joeyu930's picture
First Push
d474718 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7146864533424377,
"min": 0.7146864533424377,
"max": 2.8399970531463623,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6792.3798828125,
"min": 6792.3798828125,
"max": 28990.689453125,
"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": 12.662254333496094,
"min": 0.4377877116203308,
"max": 12.662254333496094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2469.1396484375,
"min": 84.93081665039062,
"max": 2557.776123046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06522222419190862,
"min": 0.06161480217683586,
"max": 0.0773093051002612,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2608888967676345,
"min": 0.25853211006210136,
"max": 0.3562191783635439,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1943518849929758,
"min": 0.13841293848977954,
"max": 0.27546716215563755,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7774075399719031,
"min": 0.5536517539591181,
"max": 1.3773358107781877,
"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": 24.704545454545453,
"min": 3.409090909090909,
"max": 25.01818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1087.0,
"min": 150.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.704545454545453,
"min": 3.409090909090909,
"max": 25.01818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1087.0,
"min": 150.0,
"max": 1376.0,
"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": "1748075136",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748075668"
},
"total": 532.02478205,
"count": 1,
"self": 0.49031805999993594,
"children": {
"run_training.setup": {
"total": 0.03781334500001776,
"count": 1,
"self": 0.03781334500001776
},
"TrainerController.start_learning": {
"total": 531.496650645,
"count": 1,
"self": 0.46661692899567697,
"children": {
"TrainerController._reset_env": {
"total": 3.745671540999979,
"count": 1,
"self": 3.745671540999979
},
"TrainerController.advance": {
"total": 527.1813802640045,
"count": 18192,
"self": 0.5234745330096757,
"children": {
"env_step": {
"total": 380.72305706899795,
"count": 18192,
"self": 291.3521721460056,
"children": {
"SubprocessEnvManager._take_step": {
"total": 89.08207069799676,
"count": 18192,
"self": 1.5735929009979372,
"children": {
"TorchPolicy.evaluate": {
"total": 87.50847779699882,
"count": 18192,
"self": 87.50847779699882
}
}
},
"workers": {
"total": 0.2888142249955763,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 529.7039072039913,
"count": 18192,
"is_parallel": true,
"self": 274.70818120798447,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005274903999975322,
"count": 1,
"is_parallel": true,
"self": 0.003424573999950553,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001850330000024769,
"count": 10,
"is_parallel": true,
"self": 0.001850330000024769
}
}
},
"UnityEnvironment.step": {
"total": 0.0452447119999988,
"count": 1,
"is_parallel": true,
"self": 0.0007799689999501425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005037350000520746,
"count": 1,
"is_parallel": true,
"self": 0.0005037350000520746
},
"communicator.exchange": {
"total": 0.041504794000047696,
"count": 1,
"is_parallel": true,
"self": 0.041504794000047696
},
"steps_from_proto": {
"total": 0.0024562139999488863,
"count": 1,
"is_parallel": true,
"self": 0.0004821879998644363,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00197402600008445,
"count": 10,
"is_parallel": true,
"self": 0.00197402600008445
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.99572599600685,
"count": 18191,
"is_parallel": true,
"self": 11.965774056003397,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.939550947003113,
"count": 18191,
"is_parallel": true,
"self": 6.939550947003113
},
"communicator.exchange": {
"total": 195.53076274600733,
"count": 18191,
"is_parallel": true,
"self": 195.53076274600733
},
"steps_from_proto": {
"total": 40.55963824699302,
"count": 18191,
"is_parallel": true,
"self": 7.388809716975743,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.170828530017275,
"count": 181910,
"is_parallel": true,
"self": 33.170828530017275
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 145.93484866199685,
"count": 18192,
"self": 0.580277177988819,
"children": {
"process_trajectory": {
"total": 33.543320912008426,
"count": 18192,
"self": 32.94892966500845,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5943912469999759,
"count": 4,
"self": 0.5943912469999759
}
}
},
"_update_policy": {
"total": 111.81125057199961,
"count": 90,
"self": 46.822148875999346,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.98910169600026,
"count": 4587,
"self": 64.98910169600026
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2190000688860891e-06,
"count": 1,
"self": 1.2190000688860891e-06
},
"TrainerController._save_models": {
"total": 0.10298069199984639,
"count": 1,
"self": 0.0010337759999856644,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10194691599986072,
"count": 1,
"self": 0.10194691599986072
}
}
}
}
}
}
}