afem/logs/before.out

419 lines
59 KiB
Plaintext

Starting training at Thu 28 May 13:25:52 CST 2026
Running on node: node06
[Device] cuda
[Env] node_feats=12 edge_feats=1 act_dim=1
[Model] params=76,099
1/401 | loss=0.8482 ev=0.001 agents=84 avg_r=-1.5801 sum_r=-404.50 x<0=0.09 elig=0.59 dorfler_tail=0.08 floor=0 sel=35 n_ref=0 r_loc=0.000 8.5s
2/401 | loss=1.0257 ev=0.010 agents=48 avg_r=-2.2743 sum_r=-582.23 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=39 n_ref=0 r_loc=0.000 8.3s
3/401 | loss=0.6731 ev=0.019 agents=156 avg_r=-2.3457 sum_r=-600.50 x<0=0.07 elig=0.58 dorfler_tail=0.09 floor=0 sel=35 n_ref=0 r_loc=0.000 7.8s
4/401 | loss=1.1435 ev=0.036 agents=246 avg_r=-3.6846 sum_r=-943.26 x<0=0.05 elig=0.59 dorfler_tail=0.07 floor=0 sel=36 n_ref=0 r_loc=0.000 7.9s
5/401 | loss=0.6883 ev=0.056 agents=158 avg_r=-1.2686 sum_r=-324.77 x<0=0.05 elig=0.58 dorfler_tail=0.09 floor=0 sel=37 n_ref=0 r_loc=0.000 8.2s
6/401 | loss=0.9416 ev=0.095 agents=142 avg_r=-0.0596 sum_r=-15.24 x<0=0.04 elig=0.59 dorfler_tail=0.07 floor=0 sel=36 n_ref=0 r_loc=0.000 8.2s
7/401 | loss=0.7991 ev=0.105 agents=164 avg_r=-1.2996 sum_r=-332.70 x<0=0.03 elig=0.59 dorfler_tail=0.08 floor=0 sel=36 n_ref=0 r_loc=0.000 8.0s
8/401 | loss=0.7861 ev=0.117 agents=133 avg_r=-0.4898 sum_r=-125.39 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=36 n_ref=0 r_loc=0.000 7.9s
9/401 | loss=0.7722 ev=0.141 agents=141 avg_r=-0.1621 sum_r=-41.50 x<0=0.02 elig=0.59 dorfler_tail=0.08 floor=0 sel=40 n_ref=0 r_loc=0.000 8.3s
10/401 | loss=1.0415 ev=0.134 agents=87 avg_r=-2.4506 sum_r=-627.35 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
11/401 | loss=0.6847 ev=0.166 agents=138 avg_r=-0.4086 sum_r=-104.60 x<0=0.01 elig=0.59 dorfler_tail=0.08 floor=0 sel=37 n_ref=0 r_loc=0.000 8.0s
12/401 | loss=0.6900 ev=0.146 agents=144 avg_r=1.5718 sum_r=402.39 x<0=0.01 elig=0.59 dorfler_tail=0.08 floor=0 sel=35 n_ref=0 r_loc=0.000 7.8s
13/401 | loss=0.9037 ev=0.191 agents=158 avg_r=-1.9889 sum_r=-509.15 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.8s
14/401 | loss=0.7577 ev=0.175 agents=175 avg_r=-1.0029 sum_r=-256.74 x<0=0.01 elig=0.59 dorfler_tail=0.08 floor=0 sel=36 n_ref=0 r_loc=0.000 7.8s
15/401 | loss=0.6942 ev=0.208 agents=78 avg_r=-0.8006 sum_r=-204.95 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.9s
16/401 | loss=0.8176 ev=0.205 agents=219 avg_r=1.1625 sum_r=297.59 x<0=0.01 elig=0.59 dorfler_tail=0.08 floor=0 sel=37 n_ref=0 r_loc=0.000 7.9s
17/401 | loss=0.5844 ev=0.178 agents=66 avg_r=-0.4453 sum_r=-114.01 x<0=0.00 elig=0.59 dorfler_tail=0.08 floor=0 sel=35 n_ref=0 r_loc=0.000 7.8s
18/401 | loss=0.9272 ev=0.198 agents=244 avg_r=-2.4742 sum_r=-633.40 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.8s
19/401 | loss=0.6133 ev=0.215 agents=34 avg_r=-1.0759 sum_r=-275.42 x<0=0.01 elig=0.59 dorfler_tail=0.08 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
20/401 | loss=0.7286 ev=0.260 agents=86 avg_r=2.3332 sum_r=597.30 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=37 n_ref=0 r_loc=0.000 7.9s
21/401 | loss=0.6750 ev=0.250 agents=102 avg_r=-0.5468 sum_r=-139.98 x<0=0.01 elig=0.59 dorfler_tail=0.08 floor=0 sel=36 n_ref=0 r_loc=0.000 7.8s
22/401 | loss=0.6968 ev=0.188 agents=133 avg_r=-0.2165 sum_r=-55.43 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.6s
23/401 | loss=0.6547 ev=0.251 agents=142 avg_r=0.7932 sum_r=203.07 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
24/401 | loss=0.7206 ev=0.221 agents=82 avg_r=-0.2919 sum_r=-74.74 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.7s
25/401 | loss=0.6633 ev=0.305 agents=235 avg_r=1.9655 sum_r=503.16 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=37 n_ref=0 r_loc=0.000 7.8s
26/401 | loss=0.7285 ev=0.215 agents=235 avg_r=-0.9946 sum_r=-254.60 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
27/401 | loss=0.6501 ev=0.264 agents=75 avg_r=-1.4324 sum_r=-366.69 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.6s
28/401 | loss=0.5842 ev=0.262 agents=34 avg_r=0.2413 sum_r=61.77 x<0=0.01 elig=0.59 dorfler_tail=0.08 floor=0 sel=36 n_ref=0 r_loc=0.000 7.7s
29/401 | loss=0.7681 ev=0.295 agents=133 avg_r=0.3315 sum_r=84.86 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.9s
30/401 | loss=0.8179 ev=0.292 agents=133 avg_r=0.4571 sum_r=117.01 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=37 n_ref=0 r_loc=0.000 8.3s
31/401 | loss=0.6542 ev=0.232 agents=131 avg_r=1.6268 sum_r=416.47 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.7s
32/401 | loss=0.5766 ev=0.204 agents=195 avg_r=-0.2509 sum_r=-64.23 x<0=0.02 elig=0.59 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.7s
33/401 | loss=0.6403 ev=0.237 agents=48 avg_r=3.0437 sum_r=779.18 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
34/401 | loss=0.7453 ev=0.291 agents=66 avg_r=-0.5863 sum_r=-150.09 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
35/401 | loss=0.6467 ev=0.303 agents=138 avg_r=1.6192 sum_r=414.51 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.7s
36/401 | loss=0.6302 ev=0.289 agents=64 avg_r=1.1951 sum_r=305.96 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.7s
37/401 | loss=0.7351 ev=0.301 agents=34 avg_r=-0.3947 sum_r=-101.03 x<0=0.01 elig=0.60 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
38/401 | loss=0.6007 ev=0.312 agents=246 avg_r=0.4709 sum_r=120.55 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
39/401 | loss=0.6316 ev=0.318 agents=138 avg_r=1.0463 sum_r=267.85 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
40/401 | loss=0.6016 ev=0.143 agents=34 avg_r=1.0658 sum_r=272.85 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
41/401 | loss=0.7033 ev=0.306 agents=60 avg_r=3.5062 sum_r=897.59 x<0=0.01 elig=0.60 dorfler_tail=0.06 floor=0 sel=37 n_ref=0 r_loc=0.000 7.8s
42/401 | loss=0.5702 ev=0.268 agents=175 avg_r=-0.2759 sum_r=-70.64 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
43/401 | loss=0.5907 ev=0.324 agents=247 avg_r=0.7705 sum_r=197.25 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
44/401 | loss=0.6398 ev=0.306 agents=48 avg_r=1.4337 sum_r=367.03 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
45/401 | loss=0.6173 ev=0.266 agents=34 avg_r=0.4788 sum_r=122.56 x<0=0.00 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.7s
46/401 | loss=0.5942 ev=0.262 agents=244 avg_r=0.2944 sum_r=75.38 x<0=0.01 elig=0.60 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
47/401 | loss=0.6930 ev=0.312 agents=86 avg_r=2.0645 sum_r=528.51 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.8s
48/401 | loss=0.6166 ev=0.265 agents=242 avg_r=-1.3247 sum_r=-339.13 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
49/401 | loss=0.6950 ev=0.281 agents=76 avg_r=0.5565 sum_r=142.46 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
50/401 | loss=0.5718 ev=0.306 agents=280 avg_r=1.5020 sum_r=384.52 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
[Checkpoint] saved → checkpoints/model_iter0050.pt
51/401 | loss=0.5765 ev=0.337 agents=48 avg_r=1.0395 sum_r=266.11 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
52/401 | loss=0.7324 ev=0.326 agents=34 avg_r=-0.5879 sum_r=-150.50 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 8.1s
53/401 | loss=0.6879 ev=0.195 agents=133 avg_r=0.2283 sum_r=58.44 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.9s
54/401 | loss=0.5093 ev=0.354 agents=34 avg_r=3.4100 sum_r=872.97 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.6s
55/401 | loss=0.5717 ev=0.241 agents=76 avg_r=0.1396 sum_r=35.73 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
56/401 | loss=0.6966 ev=0.329 agents=55 avg_r=1.8220 sum_r=466.43 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.7s
57/401 | loss=0.6618 ev=0.271 agents=53 avg_r=0.1718 sum_r=43.99 x<0=0.01 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
58/401 | loss=0.7686 ev=0.308 agents=34 avg_r=-0.3162 sum_r=-80.94 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
59/401 | loss=0.6369 ev=0.282 agents=34 avg_r=1.1943 sum_r=305.74 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.7s
60/401 | loss=0.5711 ev=0.316 agents=78 avg_r=0.4311 sum_r=110.36 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
61/401 | loss=0.6055 ev=0.243 agents=141 avg_r=0.7018 sum_r=179.65 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
62/401 | loss=0.5890 ev=0.320 agents=161 avg_r=2.4707 sum_r=632.49 x<0=0.02 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
63/401 | loss=0.7483 ev=0.299 agents=94 avg_r=-0.1036 sum_r=-26.52 x<0=0.02 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
64/401 | loss=0.5846 ev=0.308 agents=142 avg_r=2.2134 sum_r=566.62 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
65/401 | loss=0.6235 ev=0.310 agents=34 avg_r=0.3583 sum_r=91.72 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
66/401 | loss=0.7279 ev=0.340 agents=242 avg_r=0.8842 sum_r=226.36 x<0=0.03 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
67/401 | loss=0.6277 ev=0.276 agents=66 avg_r=-0.6905 sum_r=-176.76 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
68/401 | loss=0.4957 ev=0.312 agents=155 avg_r=1.7990 sum_r=460.54 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
69/401 | loss=0.6134 ev=0.315 agents=193 avg_r=0.1199 sum_r=30.69 x<0=0.03 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
70/401 | loss=0.6138 ev=0.320 agents=55 avg_r=-0.0142 sum_r=-3.63 x<0=0.04 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
71/401 | loss=0.7342 ev=0.334 agents=123 avg_r=1.7634 sum_r=451.42 x<0=0.05 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
72/401 | loss=0.6063 ev=0.314 agents=75 avg_r=0.6803 sum_r=174.15 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
73/401 | loss=0.5994 ev=0.304 agents=66 avg_r=0.3545 sum_r=90.76 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
74/401 | loss=0.6456 ev=0.337 agents=155 avg_r=0.7796 sum_r=199.57 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
75/401 | loss=0.7205 ev=0.282 agents=34 avg_r=-1.2208 sum_r=-312.52 x<0=0.05 elig=0.60 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
76/401 | loss=0.6423 ev=0.301 agents=133 avg_r=-0.0014 sum_r=-0.35 x<0=0.05 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 8.1s
77/401 | loss=0.5801 ev=0.316 agents=34 avg_r=0.9398 sum_r=240.59 x<0=0.06 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
78/401 | loss=0.8439 ev=0.291 agents=161 avg_r=0.5240 sum_r=134.15 x<0=0.07 elig=0.60 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
79/401 | loss=0.5819 ev=0.342 agents=224 avg_r=0.4114 sum_r=105.33 x<0=0.07 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.6s
80/401 | loss=0.6512 ev=0.300 agents=193 avg_r=-1.0909 sum_r=-279.28 x<0=0.08 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
81/401 | loss=0.7695 ev=0.337 agents=87 avg_r=1.4936 sum_r=382.37 x<0=0.10 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
82/401 | loss=0.4945 ev=0.261 agents=103 avg_r=0.7102 sum_r=181.81 x<0=0.09 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
83/401 | loss=0.6859 ev=0.345 agents=34 avg_r=1.0995 sum_r=281.47 x<0=0.16 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.6s
84/401 | loss=0.6656 ev=0.273 agents=111 avg_r=2.1667 sum_r=554.67 x<0=0.18 elig=0.60 dorfler_tail=0.07 floor=0 sel=36 n_ref=0 r_loc=0.000 7.6s
85/401 | loss=0.6877 ev=0.281 agents=85 avg_r=-1.2801 sum_r=-327.71 x<0=0.17 elig=0.60 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
86/401 | loss=0.6557 ev=0.299 agents=174 avg_r=1.0104 sum_r=258.67 x<0=0.18 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
87/401 | loss=0.6198 ev=0.312 agents=158 avg_r=0.2309 sum_r=59.11 x<0=0.17 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
88/401 | loss=0.6287 ev=0.358 agents=48 avg_r=1.5747 sum_r=403.13 x<0=0.17 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
89/401 | loss=0.6695 ev=0.294 agents=34 avg_r=1.2450 sum_r=318.72 x<0=0.20 elig=0.60 dorfler_tail=0.07 floor=0 sel=36 n_ref=0 r_loc=0.000 7.7s
90/401 | loss=0.6368 ev=0.292 agents=34 avg_r=-1.0354 sum_r=-265.05 x<0=0.20 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
91/401 | loss=0.5655 ev=0.267 agents=542 avg_r=1.3067 sum_r=334.51 x<0=0.23 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.6s
92/401 | loss=0.7495 ev=0.331 agents=584 avg_r=-0.3680 sum_r=-94.22 x<0=0.23 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
93/401 | loss=0.6225 ev=0.292 agents=343 avg_r=-1.3500 sum_r=-345.59 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
94/401 | loss=0.6050 ev=0.324 agents=360 avg_r=1.3880 sum_r=355.33 x<0=0.24 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
95/401 | loss=0.6482 ev=0.322 agents=142 avg_r=-0.5954 sum_r=-152.42 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
96/401 | loss=0.5924 ev=0.338 agents=258 avg_r=0.4584 sum_r=117.36 x<0=0.23 elig=0.60 dorfler_tail=0.07 floor=0 sel=36 n_ref=0 r_loc=0.000 7.6s
97/401 | loss=0.6026 ev=0.267 agents=133 avg_r=-0.5686 sum_r=-145.57 x<0=0.24 elig=0.60 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.0s
98/401 | loss=0.7563 ev=0.356 agents=665 avg_r=-0.4694 sum_r=-120.17 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
99/401 | loss=0.5980 ev=0.296 agents=899 avg_r=1.6428 sum_r=420.56 x<0=0.25 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.7s
100/401 | loss=0.6262 ev=0.318 agents=34 avg_r=-1.1789 sum_r=-301.80 x<0=0.25 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.7s
[Checkpoint] saved → checkpoints/model_iter0100.pt
101/401 | loss=0.6111 ev=0.312 agents=87 avg_r=-1.0703 sum_r=-274.00 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
102/401 | loss=0.6306 ev=0.317 agents=1082 avg_r=2.7796 sum_r=711.58 x<0=0.26 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
103/401 | loss=0.8435 ev=0.283 agents=491 avg_r=-1.3251 sum_r=-339.23 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
104/401 | loss=0.6451 ev=0.303 agents=161 avg_r=-2.2744 sum_r=-582.24 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
105/401 | loss=0.6049 ev=0.339 agents=826 avg_r=2.9649 sum_r=759.02 x<0=0.27 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
106/401 | loss=0.6847 ev=0.265 agents=294 avg_r=-3.5720 sum_r=-914.44 x<0=0.27 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
107/401 | loss=0.6118 ev=0.322 agents=188 avg_r=0.9259 sum_r=237.02 x<0=0.27 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
108/401 | loss=0.6254 ev=0.318 agents=349 avg_r=-0.1577 sum_r=-40.38 x<0=0.28 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
109/401 | loss=0.6404 ev=0.344 agents=73 avg_r=0.0348 sum_r=8.91 x<0=0.28 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
110/401 | loss=0.5885 ev=0.342 agents=158 avg_r=0.2726 sum_r=69.79 x<0=0.28 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
111/401 | loss=0.5346 ev=0.361 agents=242 avg_r=0.6142 sum_r=157.23 x<0=0.29 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.5s
112/401 | loss=0.7332 ev=0.326 agents=174 avg_r=-0.6867 sum_r=-175.79 x<0=0.28 elig=0.60 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
113/401 | loss=0.6006 ev=0.370 agents=224 avg_r=0.9889 sum_r=253.17 x<0=0.28 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
114/401 | loss=0.6385 ev=0.329 agents=219 avg_r=-0.5056 sum_r=-129.44 x<0=0.27 elig=0.60 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
115/401 | loss=0.6192 ev=0.354 agents=34 avg_r=0.2074 sum_r=53.10 x<0=0.27 elig=0.60 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
116/401 | loss=0.5917 ev=0.337 agents=48 avg_r=1.4759 sum_r=377.84 x<0=0.28 elig=0.60 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
117/401 | loss=0.7783 ev=0.327 agents=34 avg_r=-1.4926 sum_r=-382.10 x<0=0.27 elig=0.60 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
118/401 | loss=0.6173 ev=0.311 agents=174 avg_r=0.8320 sum_r=212.99 x<0=0.29 elig=0.60 dorfler_tail=0.07 floor=0 sel=36 n_ref=0 r_loc=0.000 7.6s
119/401 | loss=0.5288 ev=0.320 agents=131 avg_r=-0.1760 sum_r=-45.05 x<0=0.28 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
120/401 | loss=0.7693 ev=0.368 agents=223 avg_r=-0.4147 sum_r=-106.15 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
121/401 | loss=0.6487 ev=0.256 agents=131 avg_r=1.0145 sum_r=259.72 x<0=0.28 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
122/401 | loss=0.6790 ev=0.367 agents=34 avg_r=-1.4039 sum_r=-359.39 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.8s
123/401 | loss=0.5770 ev=0.275 agents=252 avg_r=3.0782 sum_r=788.02 x<0=0.25 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.7s
124/401 | loss=0.7664 ev=0.367 agents=403 avg_r=-1.8521 sum_r=-474.14 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
125/401 | loss=0.5949 ev=0.260 agents=620 avg_r=-0.5130 sum_r=-131.34 x<0=0.25 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
126/401 | loss=0.6167 ev=0.382 agents=1119 avg_r=0.2129 sum_r=54.51 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
127/401 | loss=0.5372 ev=0.346 agents=1267 avg_r=1.6754 sum_r=428.90 x<0=0.24 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
128/401 | loss=0.7640 ev=0.335 agents=273 avg_r=0.4446 sum_r=113.82 x<0=0.23 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
129/401 | loss=0.5504 ev=0.270 agents=1254 avg_r=-0.8846 sum_r=-226.47 x<0=0.24 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
130/401 | loss=0.5687 ev=0.387 agents=111 avg_r=0.7564 sum_r=193.63 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
131/401 | loss=0.7015 ev=0.301 agents=34 avg_r=-1.3658 sum_r=-349.63 x<0=0.22 elig=0.60 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
132/401 | loss=0.6005 ev=0.384 agents=204 avg_r=2.4500 sum_r=627.21 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
133/401 | loss=0.5434 ev=0.325 agents=526 avg_r=0.8884 sum_r=227.42 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
134/401 | loss=0.5892 ev=0.354 agents=34 avg_r=-0.7723 sum_r=-197.70 x<0=0.21 elig=0.60 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
135/401 | loss=0.5742 ev=0.352 agents=190 avg_r=0.4945 sum_r=126.58 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
136/401 | loss=0.5433 ev=0.369 agents=82 avg_r=1.3959 sum_r=357.34 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
137/401 | loss=0.6962 ev=0.361 agents=419 avg_r=1.1219 sum_r=287.20 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
138/401 | loss=0.5333 ev=0.347 agents=320 avg_r=-0.8777 sum_r=-224.69 x<0=0.20 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
139/401 | loss=0.6291 ev=0.393 agents=89 avg_r=-2.0054 sum_r=-513.38 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
140/401 | loss=0.5229 ev=0.277 agents=556 avg_r=1.0066 sum_r=257.69 x<0=0.20 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
141/401 | loss=0.7257 ev=0.369 agents=301 avg_r=1.0365 sum_r=265.35 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
142/401 | loss=0.5885 ev=0.356 agents=344 avg_r=0.2587 sum_r=66.23 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
143/401 | loss=0.6219 ev=0.407 agents=66 avg_r=-0.0013 sum_r=-0.34 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.2s
144/401 | loss=0.6111 ev=0.349 agents=429 avg_r=0.7761 sum_r=198.68 x<0=0.23 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
145/401 | loss=0.4913 ev=0.237 agents=34 avg_r=-1.9325 sum_r=-494.72 x<0=0.20 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 6.9s
146/401 | loss=0.6959 ev=0.388 agents=151 avg_r=0.5241 sum_r=134.16 x<0=0.23 elig=0.61 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
147/401 | loss=0.5916 ev=0.367 agents=226 avg_r=1.0964 sum_r=280.67 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.7s
148/401 | loss=0.6063 ev=0.321 agents=549 avg_r=-1.3176 sum_r=-337.29 x<0=0.22 elig=0.60 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
149/401 | loss=0.5880 ev=0.369 agents=144 avg_r=-0.5012 sum_r=-128.32 x<0=0.23 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
150/401 | loss=0.7330 ev=0.336 agents=93 avg_r=-0.9342 sum_r=-239.16 x<0=0.20 elig=0.62 dorfler_tail=0.06 floor=0 sel=28 n_ref=0 r_loc=0.000 7.1s
[Checkpoint] saved → checkpoints/model_iter0150.pt
151/401 | loss=0.5344 ev=0.326 agents=232 avg_r=0.5301 sum_r=135.71 x<0=0.23 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
152/401 | loss=0.4994 ev=0.361 agents=76 avg_r=1.3224 sum_r=338.52 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
153/401 | loss=0.7887 ev=0.381 agents=165 avg_r=-1.4365 sum_r=-367.74 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
154/401 | loss=0.5708 ev=0.353 agents=227 avg_r=0.6867 sum_r=175.79 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
155/401 | loss=0.5476 ev=0.372 agents=184 avg_r=-0.1764 sum_r=-45.17 x<0=0.20 elig=0.60 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
156/401 | loss=0.5947 ev=0.350 agents=296 avg_r=-0.1529 sum_r=-39.15 x<0=0.21 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
157/401 | loss=0.5219 ev=0.399 agents=66 avg_r=0.6051 sum_r=154.90 x<0=0.21 elig=0.60 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
158/401 | loss=0.6396 ev=0.393 agents=34 avg_r=0.4283 sum_r=109.63 x<0=0.19 elig=0.61 dorfler_tail=0.06 floor=0 sel=29 n_ref=0 r_loc=0.000 7.1s
159/401 | loss=0.5693 ev=0.382 agents=805 avg_r=1.2933 sum_r=331.08 x<0=0.21 elig=0.60 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
160/401 | loss=0.5833 ev=0.338 agents=84 avg_r=-1.8923 sum_r=-484.43 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
161/401 | loss=0.5746 ev=0.340 agents=549 avg_r=-0.2881 sum_r=-73.75 x<0=0.23 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
162/401 | loss=0.6617 ev=0.402 agents=144 avg_r=-0.0799 sum_r=-20.45 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
163/401 | loss=0.5360 ev=0.314 agents=87 avg_r=0.4493 sum_r=115.02 x<0=0.24 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
164/401 | loss=0.5845 ev=0.329 agents=1107 avg_r=-1.3259 sum_r=-339.43 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
165/401 | loss=0.5861 ev=0.369 agents=340 avg_r=-1.7656 sum_r=-452.00 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
166/401 | loss=0.5568 ev=0.429 agents=142 avg_r=2.4693 sum_r=632.13 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
167/401 | loss=0.6408 ev=0.325 agents=235 avg_r=-1.4679 sum_r=-375.77 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
168/401 | loss=0.5684 ev=0.360 agents=81 avg_r=-0.1609 sum_r=-41.19 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
169/401 | loss=0.6655 ev=0.398 agents=1068 avg_r=-0.0692 sum_r=-17.71 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.6s
170/401 | loss=0.5322 ev=0.278 agents=219 avg_r=-0.4841 sum_r=-123.92 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.8s
171/401 | loss=0.5651 ev=0.348 agents=175 avg_r=-0.9866 sum_r=-252.57 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
172/401 | loss=0.6972 ev=0.365 agents=200 avg_r=-1.4787 sum_r=-378.56 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
173/401 | loss=0.5219 ev=0.333 agents=75 avg_r=0.9503 sum_r=243.28 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
174/401 | loss=0.7200 ev=0.356 agents=198 avg_r=-1.1237 sum_r=-287.66 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.7s
175/401 | loss=0.5611 ev=0.380 agents=518 avg_r=0.1212 sum_r=31.02 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
176/401 | loss=0.6726 ev=0.400 agents=100 avg_r=0.6386 sum_r=163.47 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
177/401 | loss=0.4632 ev=0.317 agents=526 avg_r=0.1369 sum_r=35.05 x<0=0.25 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
178/401 | loss=0.6494 ev=0.344 agents=220 avg_r=-2.4843 sum_r=-635.98 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
179/401 | loss=0.5324 ev=0.361 agents=726 avg_r=-0.2240 sum_r=-57.34 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
180/401 | loss=0.6761 ev=0.413 agents=34 avg_r=-0.8163 sum_r=-208.97 x<0=0.23 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
181/401 | loss=0.5574 ev=0.348 agents=60 avg_r=-0.3088 sum_r=-79.05 x<0=0.23 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
182/401 | loss=0.5345 ev=0.374 agents=972 avg_r=-0.4068 sum_r=-104.14 x<0=0.24 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
183/401 | loss=0.5651 ev=0.371 agents=100 avg_r=0.0724 sum_r=18.54 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
184/401 | loss=0.7592 ev=0.345 agents=72 avg_r=-1.9106 sum_r=-489.12 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
185/401 | loss=0.5137 ev=0.370 agents=436 avg_r=1.2368 sum_r=316.62 x<0=0.22 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
186/401 | loss=0.5665 ev=0.383 agents=133 avg_r=-1.6560 sum_r=-423.93 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
187/401 | loss=0.5679 ev=0.411 agents=34 avg_r=-0.2303 sum_r=-58.95 x<0=0.21 elig=0.60 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
188/401 | loss=0.5255 ev=0.342 agents=140 avg_r=0.6738 sum_r=172.49 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
189/401 | loss=0.5645 ev=0.376 agents=898 avg_r=0.3043 sum_r=77.89 x<0=0.21 elig=0.60 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
190/401 | loss=0.5262 ev=0.374 agents=434 avg_r=0.1856 sum_r=47.52 x<0=0.22 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
191/401 | loss=0.5633 ev=0.367 agents=429 avg_r=0.6451 sum_r=165.14 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
192/401 | loss=0.7072 ev=0.389 agents=406 avg_r=-2.2003 sum_r=-563.27 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.8s
193/401 | loss=0.5323 ev=0.409 agents=337 avg_r=1.1695 sum_r=299.39 x<0=0.21 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.6s
194/401 | loss=0.6203 ev=0.342 agents=156 avg_r=-1.8071 sum_r=-462.63 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
195/401 | loss=0.5161 ev=0.402 agents=85 avg_r=-0.4427 sum_r=-113.34 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
196/401 | loss=0.6093 ev=0.379 agents=379 avg_r=-0.8613 sum_r=-220.49 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
197/401 | loss=0.6390 ev=0.417 agents=176 avg_r=-0.0713 sum_r=-18.26 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
198/401 | loss=0.5660 ev=0.373 agents=387 avg_r=-1.3506 sum_r=-345.76 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
199/401 | loss=0.4968 ev=0.332 agents=139 avg_r=-0.6881 sum_r=-176.16 x<0=0.23 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
200/401 | loss=0.5646 ev=0.403 agents=539 avg_r=1.6537 sum_r=423.34 x<0=0.24 elig=0.60 dorfler_tail=0.07 floor=0 sel=35 n_ref=0 r_loc=0.000 7.5s
[Checkpoint] saved → checkpoints/model_iter0200.pt
201/401 | loss=0.5881 ev=0.359 agents=158 avg_r=-0.6809 sum_r=-174.32 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
202/401 | loss=0.5527 ev=0.373 agents=86 avg_r=0.5753 sum_r=147.28 x<0=0.23 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
203/401 | loss=0.6413 ev=0.392 agents=824 avg_r=0.1860 sum_r=47.62 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
204/401 | loss=0.5117 ev=0.341 agents=198 avg_r=-0.4617 sum_r=-118.20 x<0=0.22 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
205/401 | loss=0.6845 ev=0.402 agents=53 avg_r=-2.0145 sum_r=-515.71 x<0=0.23 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
206/401 | loss=0.4670 ev=0.339 agents=133 avg_r=0.5982 sum_r=153.13 x<0=0.21 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 7.0s
207/401 | loss=0.5664 ev=0.369 agents=1222 avg_r=0.9834 sum_r=251.75 x<0=0.23 elig=0.60 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
208/401 | loss=0.6963 ev=0.385 agents=80 avg_r=-2.0704 sum_r=-530.03 x<0=0.19 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
209/401 | loss=0.5655 ev=0.367 agents=563 avg_r=1.0998 sum_r=281.55 x<0=0.21 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
210/401 | loss=0.5638 ev=0.385 agents=736 avg_r=-0.6709 sum_r=-171.76 x<0=0.19 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
211/401 | loss=0.4561 ev=0.421 agents=1554 avg_r=0.3749 sum_r=95.98 x<0=0.19 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
212/401 | loss=0.7065 ev=0.398 agents=34 avg_r=0.3088 sum_r=79.06 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
213/401 | loss=0.5221 ev=0.311 agents=34 avg_r=-3.9111 sum_r=-1001.24 x<0=0.21 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
214/401 | loss=0.6268 ev=0.406 agents=207 avg_r=0.6081 sum_r=155.67 x<0=0.20 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
215/401 | loss=0.6910 ev=0.417 agents=161 avg_r=-0.4418 sum_r=-113.09 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.6s
216/401 | loss=0.5559 ev=0.355 agents=300 avg_r=-0.1959 sum_r=-50.14 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
217/401 | loss=0.5544 ev=0.384 agents=133 avg_r=-2.2292 sum_r=-570.67 x<0=0.20 elig=0.60 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
218/401 | loss=0.5503 ev=0.386 agents=1380 avg_r=0.2610 sum_r=66.83 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=36 n_ref=0 r_loc=0.000 7.7s
219/401 | loss=0.5591 ev=0.380 agents=441 avg_r=-1.7828 sum_r=-456.41 x<0=0.19 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 7.0s
220/401 | loss=0.6269 ev=0.447 agents=337 avg_r=0.6625 sum_r=169.59 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
221/401 | loss=0.5442 ev=0.337 agents=48 avg_r=0.6702 sum_r=171.58 x<0=0.22 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
222/401 | loss=0.5796 ev=0.373 agents=209 avg_r=-0.7158 sum_r=-183.25 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
223/401 | loss=0.5371 ev=0.400 agents=328 avg_r=-0.1674 sum_r=-42.86 x<0=0.21 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.0s
224/401 | loss=0.6295 ev=0.416 agents=121 avg_r=-0.6457 sum_r=-165.30 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
225/401 | loss=0.4862 ev=0.367 agents=244 avg_r=1.1177 sum_r=286.12 x<0=0.23 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
226/401 | loss=0.5710 ev=0.360 agents=175 avg_r=-0.2754 sum_r=-70.49 x<0=0.23 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
227/401 | loss=0.5945 ev=0.353 agents=34 avg_r=-3.3050 sum_r=-846.07 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
228/401 | loss=0.6549 ev=0.416 agents=159 avg_r=-0.3421 sum_r=-87.59 x<0=0.21 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
229/401 | loss=0.5569 ev=0.402 agents=142 avg_r=0.4867 sum_r=124.59 x<0=0.20 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
230/401 | loss=0.6834 ev=0.416 agents=432 avg_r=-1.3377 sum_r=-342.44 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
231/401 | loss=0.5048 ev=0.346 agents=299 avg_r=-0.3187 sum_r=-81.60 x<0=0.22 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
232/401 | loss=0.7049 ev=0.413 agents=78 avg_r=-0.6128 sum_r=-156.89 x<0=0.22 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
233/401 | loss=0.4813 ev=0.343 agents=36 avg_r=0.3085 sum_r=78.97 x<0=0.21 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 6.9s
234/401 | loss=0.5862 ev=0.354 agents=333 avg_r=1.7158 sum_r=439.25 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
235/401 | loss=0.6787 ev=0.397 agents=34 avg_r=-1.9337 sum_r=-495.01 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
236/401 | loss=0.5569 ev=0.399 agents=193 avg_r=-0.9097 sum_r=-232.89 x<0=0.23 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
237/401 | loss=0.5414 ev=0.393 agents=103 avg_r=-1.4208 sum_r=-363.73 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
238/401 | loss=0.5549 ev=0.372 agents=48 avg_r=-1.0300 sum_r=-263.67 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
239/401 | loss=0.6030 ev=0.435 agents=896 avg_r=-0.1038 sum_r=-26.56 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.5s
240/401 | loss=0.5383 ev=0.320 agents=48 avg_r=0.5485 sum_r=140.41 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
241/401 | loss=0.6044 ev=0.427 agents=370 avg_r=-0.7533 sum_r=-192.84 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.7s
242/401 | loss=0.5599 ev=0.372 agents=236 avg_r=-1.5351 sum_r=-392.98 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
243/401 | loss=0.5583 ev=0.395 agents=153 avg_r=-1.1731 sum_r=-300.30 x<0=0.28 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
244/401 | loss=0.5860 ev=0.384 agents=1091 avg_r=-1.3456 sum_r=-344.48 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
245/401 | loss=0.5337 ev=0.377 agents=1349 avg_r=2.2382 sum_r=572.98 x<0=0.28 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
246/401 | loss=0.6395 ev=0.356 agents=851 avg_r=-3.1663 sum_r=-810.58 x<0=0.27 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
247/401 | loss=0.5909 ev=0.428 agents=671 avg_r=3.1579 sum_r=808.42 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
248/401 | loss=0.5679 ev=0.362 agents=219 avg_r=-4.4722 sum_r=-1144.88 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.0s
249/401 | loss=0.4965 ev=0.384 agents=112 avg_r=-1.7098 sum_r=-437.70 x<0=0.28 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
250/401 | loss=0.5453 ev=0.411 agents=185 avg_r=0.6639 sum_r=169.96 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
[Checkpoint] saved → checkpoints/model_iter0250.pt
251/401 | loss=0.6922 ev=0.377 agents=488 avg_r=-1.7138 sum_r=-438.73 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
252/401 | loss=0.5444 ev=0.395 agents=193 avg_r=0.3247 sum_r=83.11 x<0=0.28 elig=0.61 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
253/401 | loss=0.5359 ev=0.388 agents=159 avg_r=-1.5650 sum_r=-400.65 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
254/401 | loss=0.5134 ev=0.401 agents=217 avg_r=-0.0328 sum_r=-8.39 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
255/401 | loss=0.5651 ev=0.395 agents=428 avg_r=0.4327 sum_r=110.77 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
256/401 | loss=0.5563 ev=0.385 agents=497 avg_r=-0.7435 sum_r=-190.33 x<0=0.27 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
257/401 | loss=0.6860 ev=0.371 agents=34 avg_r=-0.7764 sum_r=-198.75 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
258/401 | loss=0.5434 ev=0.422 agents=1102 avg_r=-0.7016 sum_r=-179.60 x<0=0.27 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
259/401 | loss=0.5401 ev=0.403 agents=526 avg_r=-0.7190 sum_r=-184.06 x<0=0.28 elig=0.61 dorfler_tail=0.06 floor=0 sel=35 n_ref=0 r_loc=0.000 7.5s
260/401 | loss=0.5250 ev=0.369 agents=128 avg_r=-0.4536 sum_r=-116.13 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.0s
261/401 | loss=0.5151 ev=0.353 agents=293 avg_r=-0.9870 sum_r=-252.66 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.5s
262/401 | loss=0.6481 ev=0.430 agents=305 avg_r=-0.2456 sum_r=-62.88 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.6s
263/401 | loss=0.5681 ev=0.403 agents=224 avg_r=0.3445 sum_r=88.20 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
264/401 | loss=0.5175 ev=0.407 agents=112 avg_r=-0.2865 sum_r=-73.34 x<0=0.26 elig=0.60 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
265/401 | loss=0.6772 ev=0.411 agents=379 avg_r=-2.6835 sum_r=-686.99 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
266/401 | loss=0.5117 ev=0.337 agents=529 avg_r=1.9509 sum_r=499.44 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
267/401 | loss=0.6832 ev=0.418 agents=34 avg_r=-2.7091 sum_r=-693.54 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
268/401 | loss=0.5119 ev=0.416 agents=381 avg_r=-0.6775 sum_r=-173.45 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
269/401 | loss=0.6067 ev=0.360 agents=331 avg_r=-0.4300 sum_r=-110.08 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
270/401 | loss=0.5958 ev=0.361 agents=431 avg_r=-2.7872 sum_r=-713.53 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.0s
271/401 | loss=0.5430 ev=0.468 agents=250 avg_r=2.4127 sum_r=617.66 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
272/401 | loss=0.5570 ev=0.396 agents=195 avg_r=-3.9342 sum_r=-1007.15 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
273/401 | loss=0.5044 ev=0.347 agents=689 avg_r=-1.4386 sum_r=-368.28 x<0=0.27 elig=0.60 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
274/401 | loss=0.6166 ev=0.441 agents=235 avg_r=0.2971 sum_r=76.05 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
275/401 | loss=0.5763 ev=0.349 agents=245 avg_r=-1.4691 sum_r=-376.08 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
276/401 | loss=0.5384 ev=0.407 agents=275 avg_r=-1.0088 sum_r=-258.25 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
277/401 | loss=0.6362 ev=0.424 agents=244 avg_r=0.3209 sum_r=82.14 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
278/401 | loss=0.5336 ev=0.314 agents=100 avg_r=-2.8569 sum_r=-731.36 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 7.1s
279/401 | loss=0.6352 ev=0.424 agents=280 avg_r=0.4295 sum_r=109.95 x<0=0.27 elig=0.61 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
280/401 | loss=0.5223 ev=0.365 agents=280 avg_r=1.8529 sum_r=474.35 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
281/401 | loss=0.6468 ev=0.442 agents=84 avg_r=-2.3205 sum_r=-594.05 x<0=0.28 elig=0.61 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.3s
282/401 | loss=0.6596 ev=0.413 agents=472 avg_r=-0.4806 sum_r=-123.04 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
283/401 | loss=0.4776 ev=0.352 agents=72 avg_r=-1.7717 sum_r=-453.56 x<0=0.27 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
284/401 | loss=0.6458 ev=0.423 agents=159 avg_r=0.2598 sum_r=66.52 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.7s
285/401 | loss=0.6260 ev=0.352 agents=215 avg_r=-0.5077 sum_r=-129.98 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.8s
286/401 | loss=0.4547 ev=0.354 agents=259 avg_r=0.6267 sum_r=160.43 x<0=0.26 elig=0.60 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 7.1s
287/401 | loss=0.5419 ev=0.376 agents=452 avg_r=-2.1155 sum_r=-541.58 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
288/401 | loss=0.6451 ev=0.428 agents=1442 avg_r=-0.0228 sum_r=-5.83 x<0=0.27 elig=0.61 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.5s
289/401 | loss=0.5450 ev=0.397 agents=137 avg_r=1.1484 sum_r=293.99 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
290/401 | loss=0.5728 ev=0.385 agents=686 avg_r=-3.4156 sum_r=-874.40 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
291/401 | loss=0.5499 ev=0.405 agents=514 avg_r=1.9201 sum_r=491.55 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
292/401 | loss=0.5678 ev=0.381 agents=244 avg_r=-1.8899 sum_r=-483.81 x<0=0.27 elig=0.60 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
293/401 | loss=0.6316 ev=0.441 agents=224 avg_r=-2.8545 sum_r=-730.75 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
294/401 | loss=0.5186 ev=0.350 agents=100 avg_r=1.1642 sum_r=298.03 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.4s
295/401 | loss=0.6109 ev=0.428 agents=78 avg_r=-1.6792 sum_r=-429.87 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
296/401 | loss=0.5862 ev=0.366 agents=76 avg_r=-1.0895 sum_r=-278.91 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
297/401 | loss=0.6333 ev=0.441 agents=139 avg_r=-2.3314 sum_r=-596.85 x<0=0.27 elig=0.61 dorfler_tail=0.06 floor=0 sel=34 n_ref=0 r_loc=0.000 7.4s
298/401 | loss=0.5617 ev=0.398 agents=240 avg_r=-1.6337 sum_r=-418.24 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
299/401 | loss=0.4948 ev=0.320 agents=34 avg_r=0.1841 sum_r=47.12 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
300/401 | loss=0.6482 ev=0.447 agents=413 avg_r=-1.1234 sum_r=-287.59 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
[Checkpoint] saved → checkpoints/model_iter0300.pt
301/401 | loss=0.6045 ev=0.323 agents=556 avg_r=-0.8391 sum_r=-214.80 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
302/401 | loss=0.5194 ev=0.405 agents=207 avg_r=-1.0090 sum_r=-258.30 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.2s
303/401 | loss=0.5433 ev=0.412 agents=135 avg_r=-1.4167 sum_r=-362.67 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
304/401 | loss=0.5904 ev=0.305 agents=372 avg_r=-4.1354 sum_r=-1058.66 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.0s
305/401 | loss=0.6260 ev=0.441 agents=34 avg_r=-0.5323 sum_r=-136.27 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.1s
306/401 | loss=0.4904 ev=0.349 agents=165 avg_r=0.4701 sum_r=120.35 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.3s
307/401 | loss=0.6882 ev=0.399 agents=1312 avg_r=0.4548 sum_r=116.43 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
308/401 | loss=0.5244 ev=0.424 agents=887 avg_r=-1.4608 sum_r=-373.98 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.8s
309/401 | loss=0.5516 ev=0.405 agents=34 avg_r=-0.1411 sum_r=-36.12 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
310/401 | loss=0.4932 ev=0.373 agents=141 avg_r=-2.8948 sum_r=-741.06 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
311/401 | loss=0.5420 ev=0.388 agents=1335 avg_r=0.3463 sum_r=88.64 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
312/401 | loss=0.6290 ev=0.472 agents=36 avg_r=-1.9370 sum_r=-495.88 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
313/401 | loss=0.5851 ev=0.350 agents=810 avg_r=-1.9614 sum_r=-502.11 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
314/401 | loss=0.5564 ev=0.400 agents=79 avg_r=-1.1821 sum_r=-302.61 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
315/401 | loss=0.5560 ev=0.395 agents=195 avg_r=-1.6661 sum_r=-426.52 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
316/401 | loss=0.5173 ev=0.373 agents=223 avg_r=-1.4246 sum_r=-364.69 x<0=0.23 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.0s
317/401 | loss=0.5820 ev=0.378 agents=90 avg_r=-1.8654 sum_r=-477.54 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
318/401 | loss=0.5921 ev=0.454 agents=470 avg_r=1.8024 sum_r=461.43 x<0=0.26 elig=0.61 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
319/401 | loss=0.5236 ev=0.425 agents=123 avg_r=-2.1968 sum_r=-562.39 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
320/401 | loss=0.5607 ev=0.371 agents=312 avg_r=-1.6211 sum_r=-415.01 x<0=0.24 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
321/401 | loss=0.5437 ev=0.416 agents=1566 avg_r=-0.8026 sum_r=-205.46 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
322/401 | loss=0.5501 ev=0.391 agents=209 avg_r=-0.7605 sum_r=-194.70 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
323/401 | loss=0.6514 ev=0.438 agents=188 avg_r=-1.3562 sum_r=-347.19 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
324/401 | loss=0.5607 ev=0.362 agents=156 avg_r=-2.3552 sum_r=-602.93 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
325/401 | loss=0.4888 ev=0.377 agents=319 avg_r=-1.3467 sum_r=-344.77 x<0=0.23 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
326/401 | loss=0.6876 ev=0.394 agents=349 avg_r=-1.9759 sum_r=-505.83 x<0=0.26 elig=0.62 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.2s
327/401 | loss=0.6569 ev=0.451 agents=34 avg_r=-1.8179 sum_r=-465.39 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.3s
328/401 | loss=0.5126 ev=0.281 agents=152 avg_r=-0.5285 sum_r=-135.29 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 7.1s
329/401 | loss=0.5931 ev=0.450 agents=981 avg_r=-0.2140 sum_r=-54.78 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
330/401 | loss=0.5123 ev=0.339 agents=155 avg_r=-1.5693 sum_r=-401.74 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=29 n_ref=0 r_loc=0.000 7.1s
331/401 | loss=0.6416 ev=0.403 agents=34 avg_r=-1.7765 sum_r=-454.79 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.7s
332/401 | loss=0.5404 ev=0.403 agents=156 avg_r=-1.6670 sum_r=-426.76 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.8s
333/401 | loss=0.6274 ev=0.441 agents=89 avg_r=-1.2332 sum_r=-315.70 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.7s
334/401 | loss=0.5735 ev=0.352 agents=62 avg_r=-1.9856 sum_r=-508.33 x<0=0.22 elig=0.62 dorfler_tail=0.06 floor=0 sel=29 n_ref=0 r_loc=0.000 7.3s
335/401 | loss=0.4917 ev=0.352 agents=526 avg_r=0.7029 sum_r=179.95 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
336/401 | loss=0.5990 ev=0.340 agents=132 avg_r=-3.0811 sum_r=-788.76 x<0=0.23 elig=0.62 dorfler_tail=0.06 floor=0 sel=29 n_ref=0 r_loc=0.000 7.1s
337/401 | loss=0.5901 ev=0.462 agents=84 avg_r=-1.6743 sum_r=-428.62 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
338/401 | loss=0.5888 ev=0.395 agents=72 avg_r=-1.8019 sum_r=-461.30 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.5s
339/401 | loss=0.5367 ev=0.414 agents=144 avg_r=-0.9111 sum_r=-233.24 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
340/401 | loss=0.5691 ev=0.331 agents=175 avg_r=-4.5466 sum_r=-1163.92 x<0=0.26 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
341/401 | loss=0.6337 ev=0.447 agents=91 avg_r=-0.5287 sum_r=-135.34 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
342/401 | loss=0.5585 ev=0.361 agents=139 avg_r=1.2346 sum_r=316.07 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
343/401 | loss=0.5099 ev=0.408 agents=60 avg_r=-2.0503 sum_r=-524.87 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
344/401 | loss=0.5666 ev=0.390 agents=36 avg_r=-1.7931 sum_r=-459.04 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
345/401 | loss=0.5461 ev=0.404 agents=383 avg_r=-3.6997 sum_r=-947.13 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
346/401 | loss=0.7290 ev=0.376 agents=142 avg_r=0.2659 sum_r=68.08 x<0=0.26 elig=0.62 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
347/401 | loss=0.4937 ev=0.428 agents=217 avg_r=-1.5564 sum_r=-398.43 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
348/401 | loss=0.5818 ev=0.337 agents=72 avg_r=-1.5159 sum_r=-388.07 x<0=0.26 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
349/401 | loss=0.5557 ev=0.396 agents=238 avg_r=-1.6126 sum_r=-412.83 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
350/401 | loss=0.5531 ev=0.390 agents=34 avg_r=-0.3411 sum_r=-87.32 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
[Checkpoint] saved → checkpoints/model_iter0350.pt
351/401 | loss=0.5428 ev=0.398 agents=682 avg_r=-0.0545 sum_r=-13.96 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
352/401 | loss=0.5971 ev=0.375 agents=1161 avg_r=-4.0630 sum_r=-1040.14 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
353/401 | loss=0.6607 ev=0.414 agents=212 avg_r=-1.9949 sum_r=-510.68 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.1s
354/401 | loss=0.5486 ev=0.378 agents=83 avg_r=-0.9611 sum_r=-246.04 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
355/401 | loss=0.5905 ev=0.379 agents=1077 avg_r=-2.1700 sum_r=-555.53 x<0=0.26 elig=0.62 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 8.0s
356/401 | loss=0.5469 ev=0.389 agents=140 avg_r=-1.3158 sum_r=-336.85 x<0=0.26 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.6s
357/401 | loss=0.5095 ev=0.397 agents=764 avg_r=-0.0966 sum_r=-24.72 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.7s
358/401 | loss=0.5770 ev=0.395 agents=125 avg_r=-2.5987 sum_r=-665.27 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.4s
359/401 | loss=0.6685 ev=0.406 agents=103 avg_r=-3.2896 sum_r=-842.13 x<0=0.23 elig=0.63 dorfler_tail=0.06 floor=0 sel=29 n_ref=0 r_loc=0.000 7.2s
360/401 | loss=0.5382 ev=0.408 agents=537 avg_r=0.4558 sum_r=116.70 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=34 n_ref=0 r_loc=0.000 7.7s
361/401 | loss=0.5846 ev=0.384 agents=245 avg_r=-1.1329 sum_r=-290.03 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
362/401 | loss=0.5318 ev=0.404 agents=194 avg_r=-1.1031 sum_r=-282.39 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
363/401 | loss=0.6778 ev=0.410 agents=155 avg_r=-3.5161 sum_r=-900.13 x<0=0.25 elig=0.63 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.8s
364/401 | loss=0.5592 ev=0.387 agents=720 avg_r=-3.1739 sum_r=-812.52 x<0=0.25 elig=0.61 dorfler_tail=0.06 floor=0 sel=29 n_ref=0 r_loc=0.000 7.2s
365/401 | loss=0.5257 ev=0.340 agents=195 avg_r=1.4110 sum_r=361.21 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
366/401 | loss=0.7202 ev=0.381 agents=64 avg_r=-3.0263 sum_r=-774.72 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
367/401 | loss=0.5865 ev=0.393 agents=584 avg_r=-2.2033 sum_r=-564.05 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
368/401 | loss=0.5074 ev=0.411 agents=78 avg_r=-2.5681 sum_r=-657.44 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
369/401 | loss=0.5519 ev=0.377 agents=183 avg_r=0.4932 sum_r=126.27 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
370/401 | loss=0.5265 ev=0.397 agents=183 avg_r=-1.9064 sum_r=-488.03 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.4s
371/401 | loss=0.6248 ev=0.468 agents=325 avg_r=-1.4349 sum_r=-367.34 x<0=0.23 elig=0.62 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
372/401 | loss=0.6210 ev=0.368 agents=195 avg_r=-2.1573 sum_r=-552.26 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
373/401 | loss=0.5398 ev=0.381 agents=1257 avg_r=0.1999 sum_r=51.16 x<0=0.24 elig=0.61 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.5s
374/401 | loss=0.7041 ev=0.437 agents=140 avg_r=-2.6638 sum_r=-681.93 x<0=0.24 elig=0.63 dorfler_tail=0.06 floor=0 sel=28 n_ref=0 r_loc=0.000 7.0s
375/401 | loss=0.5560 ev=0.344 agents=1153 avg_r=-4.6746 sum_r=-1196.70 x<0=0.26 elig=0.62 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
376/401 | loss=0.5135 ev=0.402 agents=145 avg_r=0.4112 sum_r=105.26 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=29 n_ref=0 r_loc=0.000 7.1s
377/401 | loss=0.5797 ev=0.389 agents=476 avg_r=-1.3227 sum_r=-338.62 x<0=0.26 elig=0.62 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.6s
378/401 | loss=0.5229 ev=0.401 agents=80 avg_r=-1.8801 sum_r=-481.30 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
379/401 | loss=0.5683 ev=0.371 agents=94 avg_r=-2.1285 sum_r=-544.89 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=33 n_ref=0 r_loc=0.000 8.0s
380/401 | loss=0.5654 ev=0.402 agents=196 avg_r=-2.9217 sum_r=-747.96 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.6s
381/401 | loss=0.6029 ev=0.422 agents=76 avg_r=0.8416 sum_r=215.45 x<0=0.25 elig=0.63 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.6s
382/401 | loss=0.5868 ev=0.403 agents=202 avg_r=-3.3551 sum_r=-858.92 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.8s
383/401 | loss=0.5493 ev=0.371 agents=759 avg_r=-1.1757 sum_r=-300.97 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.4s
384/401 | loss=0.5628 ev=0.398 agents=286 avg_r=-2.6977 sum_r=-690.62 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.5s
385/401 | loss=0.5984 ev=0.329 agents=79 avg_r=-0.9978 sum_r=-255.44 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.4s
386/401 | loss=0.6295 ev=0.474 agents=112 avg_r=-2.3561 sum_r=-603.16 x<0=0.25 elig=0.63 dorfler_tail=0.06 floor=0 sel=32 n_ref=0 r_loc=0.000 7.6s
387/401 | loss=0.5699 ev=0.372 agents=747 avg_r=-2.0223 sum_r=-517.72 x<0=0.25 elig=0.61 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
388/401 | loss=0.5713 ev=0.367 agents=74 avg_r=-2.6122 sum_r=-668.71 x<0=0.23 elig=0.63 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.4s
389/401 | loss=0.5408 ev=0.380 agents=34 avg_r=-0.7515 sum_r=-192.39 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
390/401 | loss=0.5509 ev=0.404 agents=185 avg_r=-1.0922 sum_r=-279.60 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=31 n_ref=0 r_loc=0.000 7.5s
391/401 | loss=0.7629 ev=0.392 agents=1114 avg_r=-2.8317 sum_r=-724.91 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
392/401 | loss=0.5248 ev=0.384 agents=204 avg_r=0.4260 sum_r=109.06 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=33 n_ref=0 r_loc=0.000 7.7s
393/401 | loss=0.5672 ev=0.383 agents=84 avg_r=-1.4752 sum_r=-377.66 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
394/401 | loss=0.5358 ev=0.420 agents=136 avg_r=-2.7112 sum_r=-694.07 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
395/401 | loss=0.5721 ev=0.385 agents=123 avg_r=-0.5855 sum_r=-149.88 x<0=0.25 elig=0.62 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.5s
396/401 | loss=0.6814 ev=0.430 agents=769 avg_r=-2.4388 sum_r=-624.33 x<0=0.25 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.3s
397/401 | loss=0.4945 ev=0.420 agents=196 avg_r=-1.5640 sum_r=-400.38 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=32 n_ref=0 r_loc=0.000 7.6s
398/401 | loss=0.5281 ev=0.308 agents=179 avg_r=-1.0618 sum_r=-271.83 x<0=0.24 elig=0.62 dorfler_tail=0.07 floor=0 sel=30 n_ref=0 r_loc=0.000 7.2s
399/401 | loss=0.7013 ev=0.408 agents=177 avg_r=-3.2987 sum_r=-844.47 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=30 n_ref=0 r_loc=0.000 7.4s
400/401 | loss=0.5656 ev=0.374 agents=1732 avg_r=-1.8509 sum_r=-473.83 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.3s
[Checkpoint] saved → checkpoints/model_iter0400.pt
401/401 | loss=0.5597 ev=0.432 agents=220 avg_r=-2.2646 sum_r=-579.72 x<0=0.24 elig=0.62 dorfler_tail=0.06 floor=0 sel=31 n_ref=0 r_loc=0.000 7.4s
[Checkpoint] saved → checkpoints/model_iter0401.pt
[Checkpoint] saved → checkpoints/model_final.pt
[Train] done, total time 2975.5s
Training finished at Thu 28 May 14:15:44 CST 2026