Jonedowe's picture
First Push
f822d7c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7072889804840088,
"min": 0.7072889804840088,
"max": 2.8580689430236816,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6722.07421875,
"min": 6722.07421875,
"max": 29175.16796875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.96137809753418,
"min": 0.4758208692073822,
"max": 12.96137809753418,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2527.46875,
"min": 92.30924987792969,
"max": 2617.295166015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07316345068301969,
"min": 0.06355535552646353,
"max": 0.07391556329767257,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29265380273207875,
"min": 0.25422142210585413,
"max": 0.36957781648836285,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18440117102627662,
"min": 0.14427869272870286,
"max": 0.27172679719971676,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7376046841051065,
"min": 0.5771147709148114,
"max": 1.3586339859985839,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.954545454545453,
"min": 4.181818181818182,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 184.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 4.181818181818182,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 184.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1767808617",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767809063"
},
"total": 445.7367266619999,
"count": 1,
"self": 0.40417710000019724,
"children": {
"run_training.setup": {
"total": 0.034162874999765336,
"count": 1,
"self": 0.034162874999765336
},
"TrainerController.start_learning": {
"total": 445.29838668699995,
"count": 1,
"self": 0.39683331500418717,
"children": {
"TrainerController._reset_env": {
"total": 1.9868256319996362,
"count": 1,
"self": 1.9868256319996362
},
"TrainerController.advance": {
"total": 442.83588241899633,
"count": 18192,
"self": 0.4022767789683712,
"children": {
"env_step": {
"total": 322.55027839503646,
"count": 18192,
"self": 253.062591656957,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.25163306901686,
"count": 18192,
"self": 1.2819541720186862,
"children": {
"TorchPolicy.evaluate": {
"total": 67.96967889699818,
"count": 18192,
"self": 67.96967889699818
}
}
},
"workers": {
"total": 0.23605366906258496,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.53020948998847,
"count": 18192,
"is_parallel": true,
"self": 221.45900555597063,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018626470000526751,
"count": 1,
"is_parallel": true,
"self": 0.0005889090007258346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012737379993268405,
"count": 10,
"is_parallel": true,
"self": 0.0012737379993268405
}
}
},
"UnityEnvironment.step": {
"total": 0.03505800899984024,
"count": 1,
"is_parallel": true,
"self": 0.0005717409999306255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004156569998485793,
"count": 1,
"is_parallel": true,
"self": 0.0004156569998485793
},
"communicator.exchange": {
"total": 0.032143543000074715,
"count": 1,
"is_parallel": true,
"self": 0.032143543000074715
},
"steps_from_proto": {
"total": 0.0019270679999863205,
"count": 1,
"is_parallel": true,
"self": 0.0003716350006470748,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015554329993392457,
"count": 10,
"is_parallel": true,
"self": 0.0015554329993392457
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 222.07120393401783,
"count": 18191,
"is_parallel": true,
"self": 10.2265422000346,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.507841897005164,
"count": 18191,
"is_parallel": true,
"self": 5.507841897005164
},
"communicator.exchange": {
"total": 170.1940210470034,
"count": 18191,
"is_parallel": true,
"self": 170.1940210470034
},
"steps_from_proto": {
"total": 36.14279878997468,
"count": 18191,
"is_parallel": true,
"self": 6.642053805883734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.500744984090943,
"count": 181910,
"is_parallel": true,
"self": 29.500744984090943
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.8833272449915,
"count": 18192,
"self": 0.4919612699945901,
"children": {
"process_trajectory": {
"total": 25.894227271000545,
"count": 18192,
"self": 25.53389043800007,
"children": {
"RLTrainer._checkpoint": {
"total": 0.36033683300047414,
"count": 4,
"self": 0.36033683300047414
}
}
},
"_update_policy": {
"total": 93.49713870399637,
"count": 90,
"self": 37.94205032600121,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.55508837799516,
"count": 4587,
"self": 55.55508837799516
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.570000318286475e-07,
"count": 1,
"self": 8.570000318286475e-07
},
"TrainerController._save_models": {
"total": 0.07884446399975786,
"count": 1,
"self": 0.0007149569996727223,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07812950700008514,
"count": 1,
"self": 0.07812950700008514
}
}
}
}
}
}
}