ppo-Huggy / run_logs /timers.json
torayeff's picture
Huggy
e1c9150
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4057514667510986,
"min": 1.4057514667510986,
"max": 1.4267359972000122,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69773.0703125,
"min": 67346.640625,
"max": 77671.6328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.60956175298804,
"min": 93.00190114068441,
"max": 420.07563025210084,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49502.0,
"min": 48919.0,
"max": 50079.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49702.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49702.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3338403701782227,
"min": 0.061397165060043335,
"max": 2.40956974029541,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1171.587890625,
"min": 7.244865417480469,
"max": 1262.4718017578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7431153358216305,
"min": 1.7579882730871945,
"max": 3.851615012046134,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1879.0438985824585,
"min": 207.44261622428894,
"max": 1977.489827156067,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7431153358216305,
"min": 1.7579882730871945,
"max": 3.851615012046134,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1879.0438985824585,
"min": 207.44261622428894,
"max": 1977.489827156067,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016526105990305948,
"min": 0.014255501694666842,
"max": 0.02014799443713855,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.033052211980611895,
"min": 0.028511003389333683,
"max": 0.0592175012313722,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053295310524602735,
"min": 0.022760969338317713,
"max": 0.062022069469094276,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10659062104920547,
"min": 0.045521938676635426,
"max": 0.16725876331329345,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.996248667950003e-06,
"min": 3.996248667950003e-06,
"max": 0.0002952777765740749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.992497335900006e-06,
"min": 7.992497335900006e-06,
"max": 0.0008439013686995498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10133204999999998,
"min": 0.10133204999999998,
"max": 0.198425925,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20266409999999996,
"min": 0.20266409999999996,
"max": 0.5813004500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.646929500000008e-05,
"min": 7.646929500000008e-05,
"max": 0.004921453657499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015293859000000017,
"min": 0.00015293859000000017,
"max": 0.014066892455,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674419238",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1674421472"
},
"total": 2233.990637418,
"count": 1,
"self": 0.3869920980000643,
"children": {
"run_training.setup": {
"total": 0.11042898599998807,
"count": 1,
"self": 0.11042898599998807
},
"TrainerController.start_learning": {
"total": 2233.493216334,
"count": 1,
"self": 3.9557754549737183,
"children": {
"TrainerController._reset_env": {
"total": 9.399940620000052,
"count": 1,
"self": 9.399940620000052
},
"TrainerController.advance": {
"total": 2220.0198191010263,
"count": 231255,
"self": 4.0975251309673695,
"children": {
"env_step": {
"total": 1775.7796037409903,
"count": 231255,
"self": 1492.4393493348648,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.7369255929748,
"count": 231255,
"self": 14.815338546049475,
"children": {
"TorchPolicy.evaluate": {
"total": 265.9215870469253,
"count": 222982,
"self": 66.72277724896526,
"children": {
"TorchPolicy.sample_actions": {
"total": 199.19880979796005,
"count": 222982,
"self": 199.19880979796005
}
}
}
}
},
"workers": {
"total": 2.6033288131507106,
"count": 231255,
"self": 0.0,
"children": {
"worker_root": {
"total": 2222.771737751083,
"count": 231255,
"is_parallel": true,
"self": 995.5687423302384,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002145281000025534,
"count": 1,
"is_parallel": true,
"self": 0.00033530600001085986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018099750000146742,
"count": 2,
"is_parallel": true,
"self": 0.0018099750000146742
}
}
},
"UnityEnvironment.step": {
"total": 0.028001626999980544,
"count": 1,
"is_parallel": true,
"self": 0.00027564700008042564,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002068259999532529,
"count": 1,
"is_parallel": true,
"self": 0.0002068259999532529
},
"communicator.exchange": {
"total": 0.026848420999954214,
"count": 1,
"is_parallel": true,
"self": 0.026848420999954214
},
"steps_from_proto": {
"total": 0.0006707329999926515,
"count": 1,
"is_parallel": true,
"self": 0.00022082899999986694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004499039999927845,
"count": 2,
"is_parallel": true,
"self": 0.0004499039999927845
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1227.2029954208447,
"count": 231254,
"is_parallel": true,
"self": 35.05506117360892,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.02603491103503,
"count": 231254,
"is_parallel": true,
"self": 84.02603491103503
},
"communicator.exchange": {
"total": 1012.4412012601415,
"count": 231254,
"is_parallel": true,
"self": 1012.4412012601415
},
"steps_from_proto": {
"total": 95.68069807605946,
"count": 231254,
"is_parallel": true,
"self": 41.061743084139835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.61895499191962,
"count": 462508,
"is_parallel": true,
"self": 54.61895499191962
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 440.14269022906876,
"count": 231255,
"self": 6.188896111856138,
"children": {
"process_trajectory": {
"total": 142.94114789721255,
"count": 231255,
"self": 141.79003153421354,
"children": {
"RLTrainer._checkpoint": {
"total": 1.151116362999005,
"count": 10,
"self": 1.151116362999005
}
}
},
"_update_policy": {
"total": 291.0126462200001,
"count": 96,
"self": 239.08216743100286,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.93047878899722,
"count": 2880,
"self": 51.93047878899722
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.359996511193458e-07,
"count": 1,
"self": 9.359996511193458e-07
},
"TrainerController._save_models": {
"total": 0.11768022200021733,
"count": 1,
"self": 0.0021239060001789767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11555631600003835,
"count": 1,
"self": 0.11555631600003835
}
}
}
}
}
}
}