sjin59's picture
First Push
407c209 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0943589210510254,
"min": 1.0876834392547607,
"max": 2.818800687789917,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10400.787109375,
"min": 10400.787109375,
"max": 28774.31640625,
"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": 11.854597091674805,
"min": 0.37790200114250183,
"max": 11.854597091674805,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2311.646484375,
"min": 73.31298828125,
"max": 2394.50146484375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06900561609604755,
"min": 0.06132557657986706,
"max": 0.07598330315069653,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2760224643841902,
"min": 0.2521137369878809,
"max": 0.3756314684413191,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1976841802836633,
"min": 0.12565016973759138,
"max": 0.2672959504028161,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7907367211346532,
"min": 0.5026006789503655,
"max": 1.3069530862803553,
"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": 23.431818181818183,
"min": 3.772727272727273,
"max": 23.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1031.0,
"min": 166.0,
"max": 1290.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.431818181818183,
"min": 3.772727272727273,
"max": 23.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1031.0,
"min": 166.0,
"max": 1290.0,
"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": "1777897784",
"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": "1777898261"
},
"total": 477.33543251800006,
"count": 1,
"self": 0.4788015720000658,
"children": {
"run_training.setup": {
"total": 0.02422548099980304,
"count": 1,
"self": 0.02422548099980304
},
"TrainerController.start_learning": {
"total": 476.8324054650002,
"count": 1,
"self": 0.41703768002525976,
"children": {
"TrainerController._reset_env": {
"total": 3.3371797670001797,
"count": 1,
"self": 3.3371797670001797
},
"TrainerController.advance": {
"total": 472.99605552197454,
"count": 18192,
"self": 0.43244632499249747,
"children": {
"env_step": {
"total": 347.1313541479758,
"count": 18192,
"self": 269.8964154660075,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.982611200973,
"count": 18192,
"self": 1.3598620549671523,
"children": {
"TorchPolicy.evaluate": {
"total": 75.62274914600584,
"count": 18192,
"self": 75.62274914600584
}
}
},
"workers": {
"total": 0.2523274809952909,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.9608895990036,
"count": 18192,
"is_parallel": true,
"self": 238.29199379699435,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005525070999965465,
"count": 1,
"is_parallel": true,
"self": 0.00384889599968119,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016761750002842746,
"count": 10,
"is_parallel": true,
"self": 0.0016761750002842746
}
}
},
"UnityEnvironment.step": {
"total": 0.037433903999954055,
"count": 1,
"is_parallel": true,
"self": 0.0006272089999583841,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040194799998971575,
"count": 1,
"is_parallel": true,
"self": 0.00040194799998971575
},
"communicator.exchange": {
"total": 0.03435426900000493,
"count": 1,
"is_parallel": true,
"self": 0.03435426900000493
},
"steps_from_proto": {
"total": 0.0020504780000010214,
"count": 1,
"is_parallel": true,
"self": 0.0003876890002629807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016627889997380407,
"count": 10,
"is_parallel": true,
"self": 0.0016627889997380407
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.66889580200927,
"count": 18191,
"is_parallel": true,
"self": 10.851677478017564,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.934990488015501,
"count": 18191,
"is_parallel": true,
"self": 5.934990488015501
},
"communicator.exchange": {
"total": 179.73932866898917,
"count": 18191,
"is_parallel": true,
"self": 179.73932866898917
},
"steps_from_proto": {
"total": 40.142899166987036,
"count": 18191,
"is_parallel": true,
"self": 6.96689382801992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.176005338967116,
"count": 181910,
"is_parallel": true,
"self": 33.176005338967116
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.43225504900624,
"count": 18192,
"self": 0.49858337599675906,
"children": {
"process_trajectory": {
"total": 27.52577444300846,
"count": 18192,
"self": 27.123383979008167,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4023904640002911,
"count": 4,
"self": 0.4023904640002911
}
}
},
"_update_policy": {
"total": 97.40789723000103,
"count": 90,
"self": 40.204800010003964,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.20309721999706,
"count": 4587,
"self": 57.20309721999706
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1590000212891027e-06,
"count": 1,
"self": 1.1590000212891027e-06
},
"TrainerController._save_models": {
"total": 0.0821313370001917,
"count": 1,
"self": 0.000686109000525903,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0814452279996658,
"count": 1,
"self": 0.0814452279996658
}
}
}
}
}
}
}