13 lines
1.1 KiB
Plaintext
13 lines
1.1 KiB
Plaintext
[2025-10-11 22:35:43,673][__main__][INFO] - Training for 50000 timesteps with NormalQNetwork and NormalReplayBuffer
|
|
[2025-10-11 22:35:53,175][core][INFO] - Step: 2000, Eval mean: 9.4, Eval std: 0.66332495807108
|
|
[2025-10-11 22:36:04,147][core][INFO] - Step: 4000, Eval mean: 25.2, Eval std: 2.1354156504062622
|
|
[2025-10-11 22:36:14,701][core][INFO] - Step: 6000, Eval mean: 9.4, Eval std: 0.66332495807108
|
|
[2025-10-11 22:36:25,593][core][INFO] - Step: 8000, Eval mean: 9.4, Eval std: 0.66332495807108
|
|
[2025-10-11 22:36:36,771][core][INFO] - Step: 10000, Eval mean: 9.4, Eval std: 0.66332495807108
|
|
[2025-10-11 22:36:48,501][core][INFO] - Step: 12000, Eval mean: 13.2, Eval std: 0.9797958971132712
|
|
[2025-10-11 22:37:00,186][core][INFO] - Step: 14000, Eval mean: 9.2, Eval std: 0.6
|
|
[2025-10-11 22:37:12,253][core][INFO] - Step: 16000, Eval mean: 9.2, Eval std: 0.6
|
|
[2025-10-11 22:37:24,363][core][INFO] - Step: 18000, Eval mean: 12.6, Eval std: 1.4966629547095764
|
|
[2025-10-11 22:37:37,055][core][INFO] - Step: 20000, Eval mean: 12.9, Eval std: 1.0440306508910548
|
|
[2025-10-11 22:37:49,427][core][INFO] - Step: 22000, Eval mean: 9.2, Eval std: 0.6
|