Lakoc's picture
PPO agent
38b64b8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8671228885650635,
"min": 0.8671228885650635,
"max": 2.8628883361816406,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8279.2890625,
"min": 8279.2890625,
"max": 29318.83984375,
"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": 11.799769401550293,
"min": 0.3692221939563751,
"max": 11.799769401550293,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2300.955078125,
"min": 71.62910461425781,
"max": 2390.14990234375,
"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": 0.07191819698203414,
"min": 0.06354364097784912,
"max": 0.07550128024327113,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28767278792813655,
"min": 0.2645876291780594,
"max": 0.37750640121635565,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2105891665115076,
"min": 0.12551219030808403,
"max": 0.2829628416720559,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8423566660460304,
"min": 0.5020487612323361,
"max": 1.4148142083602793,
"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": 23.40909090909091,
"min": 3.477272727272727,
"max": 23.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1030.0,
"min": 153.0,
"max": 1284.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.40909090909091,
"min": 3.477272727272727,
"max": 23.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1030.0,
"min": 153.0,
"max": 1284.0,
"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": "1675261053",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675261628"
},
"total": 575.203368527,
"count": 1,
"self": 0.5961157789998879,
"children": {
"run_training.setup": {
"total": 0.1630058260000169,
"count": 1,
"self": 0.1630058260000169
},
"TrainerController.start_learning": {
"total": 574.444246922,
"count": 1,
"self": 0.8295573869946793,
"children": {
"TrainerController._reset_env": {
"total": 6.825437357999988,
"count": 1,
"self": 6.825437357999988
},
"TrainerController.advance": {
"total": 566.6371285190054,
"count": 18202,
"self": 0.4226189500092232,
"children": {
"env_step": {
"total": 566.2145095689962,
"count": 18202,
"self": 418.0521604179948,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.69770086699828,
"count": 18202,
"self": 2.3697474069965097,
"children": {
"TorchPolicy.evaluate": {
"total": 145.32795346000177,
"count": 18202,
"self": 22.39484436900841,
"children": {
"TorchPolicy.sample_actions": {
"total": 122.93310909099336,
"count": 18202,
"self": 122.93310909099336
}
}
}
}
},
"workers": {
"total": 0.4646482840030899,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 572.6615291719955,
"count": 18202,
"is_parallel": true,
"self": 263.2552427629926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006620918000010079,
"count": 1,
"is_parallel": true,
"self": 0.003921496000089064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026994219999210145,
"count": 10,
"is_parallel": true,
"self": 0.0026994219999210145
}
}
},
"UnityEnvironment.step": {
"total": 0.042717537999976685,
"count": 1,
"is_parallel": true,
"self": 0.0006901759999777823,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005352669999751924,
"count": 1,
"is_parallel": true,
"self": 0.0005352669999751924
},
"communicator.exchange": {
"total": 0.0388217230000123,
"count": 1,
"is_parallel": true,
"self": 0.0388217230000123
},
"steps_from_proto": {
"total": 0.0026703720000114117,
"count": 1,
"is_parallel": true,
"self": 0.0007199819999641477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001950390000047264,
"count": 10,
"is_parallel": true,
"self": 0.001950390000047264
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 309.4062864090029,
"count": 18201,
"is_parallel": true,
"self": 11.801949416986815,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.349003460010806,
"count": 18201,
"is_parallel": true,
"self": 8.349003460010806
},
"communicator.exchange": {
"total": 241.34680332600544,
"count": 18201,
"is_parallel": true,
"self": 241.34680332600544
},
"steps_from_proto": {
"total": 47.90853020599985,
"count": 18201,
"is_parallel": true,
"self": 11.376376546990684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.53215365900917,
"count": 182010,
"is_parallel": true,
"self": 36.53215365900917
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.748000000949105e-05,
"count": 1,
"self": 5.748000000949105e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 560.424258126987,
"count": 542720,
"is_parallel": true,
"self": 17.058755141990105,
"children": {
"process_trajectory": {
"total": 307.3718963209971,
"count": 542720,
"is_parallel": true,
"self": 306.3925595719971,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9793367490000264,
"count": 4,
"is_parallel": true,
"self": 0.9793367490000264
}
}
},
"_update_policy": {
"total": 235.99360666399974,
"count": 90,
"is_parallel": true,
"self": 55.96595560099928,
"children": {
"TorchPPOOptimizer.update": {
"total": 180.02765106300046,
"count": 4587,
"is_parallel": true,
"self": 180.02765106300046
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15206617800004096,
"count": 1,
"self": 0.0012826670000549711,
"children": {
"RLTrainer._checkpoint": {
"total": 0.150783510999986,
"count": 1,
"self": 0.150783510999986
}
}
}
}
}
}
}