nbzy1995's picture
First Push
61bc67f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9363805055618286,
"min": 0.9354673624038696,
"max": 2.864520788192749,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8899.3603515625,
"min": 8899.3603515625,
"max": 29241.02734375,
"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": 13.21750545501709,
"min": 0.2938240170478821,
"max": 13.21750545501709,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2577.41357421875,
"min": 57.001861572265625,
"max": 2658.615234375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06382039753264632,
"min": 0.06222144519580943,
"max": 0.07234480720469447,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25528159013058527,
"min": 0.25528159013058527,
"max": 0.35000908844870304,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19069785821963758,
"min": 0.11760559357593164,
"max": 0.31395415625735823,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7627914328785503,
"min": 0.4704223743037266,
"max": 1.391786430980645,
"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": 26.25,
"min": 3.159090909090909,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1155.0,
"min": 139.0,
"max": 1432.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.25,
"min": 3.159090909090909,
"max": 26.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1155.0,
"min": 139.0,
"max": 1432.0,
"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": "1744988468",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1744988888"
},
"total": 419.937342606,
"count": 1,
"self": 0.43128110999998626,
"children": {
"run_training.setup": {
"total": 0.02901608000001943,
"count": 1,
"self": 0.02901608000001943
},
"TrainerController.start_learning": {
"total": 419.477045416,
"count": 1,
"self": 0.3424613579963989,
"children": {
"TrainerController._reset_env": {
"total": 3.2489745760000233,
"count": 1,
"self": 3.2489745760000233
},
"TrainerController.advance": {
"total": 415.7802689450035,
"count": 18192,
"self": 0.3463511140173523,
"children": {
"env_step": {
"total": 292.5464077909885,
"count": 18192,
"self": 222.08111593497972,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.26210055099978,
"count": 18192,
"self": 1.2457565359909495,
"children": {
"TorchPolicy.evaluate": {
"total": 69.01634401500883,
"count": 18192,
"self": 69.01634401500883
}
}
},
"workers": {
"total": 0.20319130500899973,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 418.09072708799977,
"count": 18192,
"is_parallel": true,
"self": 223.1737296330009,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050191120000135925,
"count": 1,
"is_parallel": true,
"self": 0.003625278999948023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013938330000655696,
"count": 10,
"is_parallel": true,
"self": 0.0013938330000655696
}
}
},
"UnityEnvironment.step": {
"total": 0.03651060699996833,
"count": 1,
"is_parallel": true,
"self": 0.0005438230000436306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003862109999772656,
"count": 1,
"is_parallel": true,
"self": 0.0003862109999772656
},
"communicator.exchange": {
"total": 0.03370812799994383,
"count": 1,
"is_parallel": true,
"self": 0.03370812799994383
},
"steps_from_proto": {
"total": 0.0018724450000036086,
"count": 1,
"is_parallel": true,
"self": 0.0003660550000859075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001506389999917701,
"count": 10,
"is_parallel": true,
"self": 0.001506389999917701
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 194.91699745499886,
"count": 18191,
"is_parallel": true,
"self": 9.478817922996768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.345753404999982,
"count": 18191,
"is_parallel": true,
"self": 5.345753404999982
},
"communicator.exchange": {
"total": 149.59002181499807,
"count": 18191,
"is_parallel": true,
"self": 149.59002181499807
},
"steps_from_proto": {
"total": 30.502404312004046,
"count": 18191,
"is_parallel": true,
"self": 5.394212553003399,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.108191759000647,
"count": 181910,
"is_parallel": true,
"self": 25.108191759000647
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.88751003999766,
"count": 18192,
"self": 0.3979344789931929,
"children": {
"process_trajectory": {
"total": 26.764160383004537,
"count": 18192,
"self": 26.305060272004425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4591001110001116,
"count": 4,
"self": 0.4591001110001116
}
}
},
"_update_policy": {
"total": 95.72541517799993,
"count": 90,
"self": 38.18425382699547,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.54116135100446,
"count": 4587,
"self": 57.54116135100446
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.970000292014447e-07,
"count": 1,
"self": 9.970000292014447e-07
},
"TrainerController._save_models": {
"total": 0.10533954000004542,
"count": 1,
"self": 0.0008452560000478115,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1044942839999976,
"count": 1,
"self": 0.1044942839999976
}
}
}
}
}
}
}