nathan-cai's picture
First Push
0d2ac6d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8792926073074341,
"min": 0.8792926073074341,
"max": 2.8583920001983643,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8414.830078125,
"min": 8414.830078125,
"max": 29272.79296875,
"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": 12.914165496826172,
"min": 0.38867098093032837,
"max": 12.914165496826172,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.26220703125,
"min": 75.40216827392578,
"max": 2623.151611328125,
"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.Losses.PolicyLoss.mean": {
"value": 0.06651098430858624,
"min": 0.0628264790160328,
"max": 0.07574546018982872,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26604393723434494,
"min": 0.2612132011072747,
"max": 0.36021995041679183,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20823695167314774,
"min": 0.1344924333982407,
"max": 0.2758951401593638,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8329478066925909,
"min": 0.5379697335929629,
"max": 1.379475700796819,
"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.CumulativeReward.mean": {
"value": 25.318181818181817,
"min": 3.477272727272727,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 153.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 3.477272727272727,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 153.0,
"max": 1386.0,
"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": "1687901261",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687901729"
},
"total": 467.986877113,
"count": 1,
"self": 0.7307689869999763,
"children": {
"run_training.setup": {
"total": 0.043010394000020824,
"count": 1,
"self": 0.043010394000020824
},
"TrainerController.start_learning": {
"total": 467.213097732,
"count": 1,
"self": 0.4987044400054401,
"children": {
"TrainerController._reset_env": {
"total": 4.0983531969999945,
"count": 1,
"self": 4.0983531969999945
},
"TrainerController.advance": {
"total": 462.4015630449944,
"count": 18215,
"self": 0.2505783789858924,
"children": {
"env_step": {
"total": 462.1509846660085,
"count": 18215,
"self": 337.6736336900088,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.22860589499817,
"count": 18215,
"self": 1.6991236039983164,
"children": {
"TorchPolicy.evaluate": {
"total": 122.52948229099985,
"count": 18215,
"self": 122.52948229099985
}
}
},
"workers": {
"total": 0.248745081001573,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 465.4474282439996,
"count": 18215,
"is_parallel": true,
"self": 217.03751195599187,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005620610000050874,
"count": 1,
"is_parallel": true,
"self": 0.004103338000163603,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015172719998872708,
"count": 10,
"is_parallel": true,
"self": 0.0015172719998872708
}
}
},
"UnityEnvironment.step": {
"total": 0.043258102999971015,
"count": 1,
"is_parallel": true,
"self": 0.0006313669999826743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004188720000115609,
"count": 1,
"is_parallel": true,
"self": 0.0004188720000115609
},
"communicator.exchange": {
"total": 0.04014329199998201,
"count": 1,
"is_parallel": true,
"self": 0.04014329199998201
},
"steps_from_proto": {
"total": 0.0020645719999947687,
"count": 1,
"is_parallel": true,
"self": 0.0003797169999302241,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016848550000645446,
"count": 10,
"is_parallel": true,
"self": 0.0016848550000645446
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 248.4099162880077,
"count": 18214,
"is_parallel": true,
"self": 10.564975980018858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.230916295993438,
"count": 18214,
"is_parallel": true,
"self": 5.230916295993438
},
"communicator.exchange": {
"total": 198.09115196899603,
"count": 18214,
"is_parallel": true,
"self": 198.09115196899603
},
"steps_from_proto": {
"total": 34.52287204299938,
"count": 18214,
"is_parallel": true,
"self": 6.286060177997797,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.236811865001584,
"count": 182140,
"is_parallel": true,
"self": 28.236811865001584
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.96900000700407e-05,
"count": 1,
"self": 9.96900000700407e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.76025318000933,
"count": 448535,
"is_parallel": true,
"self": 9.836941555043268,
"children": {
"process_trajectory": {
"total": 253.50714362296617,
"count": 448535,
"is_parallel": true,
"self": 252.41205944996625,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0950841729999183,
"count": 4,
"is_parallel": true,
"self": 1.0950841729999183
}
}
},
"_update_policy": {
"total": 195.4161680019999,
"count": 90,
"is_parallel": true,
"self": 74.79619857999683,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.61996942200307,
"count": 4587,
"is_parallel": true,
"self": 120.61996942200307
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21437736000007135,
"count": 1,
"self": 0.0011416110000936897,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21323574899997766,
"count": 1,
"self": 0.21323574899997766
}
}
}
}
}
}
}