ppo-Huggy / run_logs /timers.json
malanevans's picture
Huggy
f3bf724
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4062833786010742,
"min": 1.4062833786010742,
"max": 1.4264073371887207,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70138.3828125,
"min": 68680.0859375,
"max": 77518.984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.3544776119403,
"min": 85.01379310344828,
"max": 394.62992125984255,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49502.0,
"min": 49115.0,
"max": 50118.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999981.0,
"min": 49567.0,
"max": 1999981.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999981.0,
"min": 49567.0,
"max": 1999981.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4681572914123535,
"min": 0.030884195119142532,
"max": 2.4681572914123535,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1322.9322509765625,
"min": 3.891408681869507,
"max": 1426.7744140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.917033901521519,
"min": 1.7119276734098556,
"max": 3.9762476640088216,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2099.530171215534,
"min": 215.7028868496418,
"max": 2257.620802819729,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.917033901521519,
"min": 1.7119276734098556,
"max": 3.9762476640088216,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2099.530171215534,
"min": 215.7028868496418,
"max": 2257.620802819729,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01930165484987406,
"min": 0.013313854805407269,
"max": 0.022285312448123783,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.057904964549622184,
"min": 0.026627709610814537,
"max": 0.058876374167448384,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05713958769208855,
"min": 0.02072974822173516,
"max": 0.06699652473131816,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17141876307626566,
"min": 0.04145949644347032,
"max": 0.20098957419395447,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4433988522333377e-06,
"min": 3.4433988522333377e-06,
"max": 0.0002952996015667999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0330196556700013e-05,
"min": 1.0330196556700013e-05,
"max": 0.0008438919187026998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114776666666665,
"min": 0.10114776666666665,
"max": 0.19843320000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30344329999999997,
"min": 0.20742480000000002,
"max": 0.5812972999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.727355666666676e-05,
"min": 6.727355666666676e-05,
"max": 0.00492181668,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020182067000000027,
"min": 0.00020182067000000027,
"max": 0.014066735269999998,
"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": "1681433281",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=Malan's Huggy --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": "1681435635"
},
"total": 2353.747545056,
"count": 1,
"self": 0.8015448260002813,
"children": {
"run_training.setup": {
"total": 0.1092610150000155,
"count": 1,
"self": 0.1092610150000155
},
"TrainerController.start_learning": {
"total": 2352.836739215,
"count": 1,
"self": 4.331993979973504,
"children": {
"TrainerController._reset_env": {
"total": 3.9498280930000647,
"count": 1,
"self": 3.9498280930000647
},
"TrainerController.advance": {
"total": 2344.4234790550267,
"count": 231626,
"self": 4.59345375692601,
"children": {
"env_step": {
"total": 1821.7895753960365,
"count": 231626,
"self": 1537.9018216909744,
"children": {
"SubprocessEnvManager._take_step": {
"total": 281.0241660140015,
"count": 231626,
"self": 16.80542346791117,
"children": {
"TorchPolicy.evaluate": {
"total": 264.2187425460903,
"count": 222924,
"self": 264.2187425460903
}
}
},
"workers": {
"total": 2.8635876910606157,
"count": 231626,
"self": 0.0,
"children": {
"worker_root": {
"total": 2344.816077918872,
"count": 231626,
"is_parallel": true,
"self": 1087.836040533798,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009668149999697562,
"count": 1,
"is_parallel": true,
"self": 0.00027000599993698415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000696809000032772,
"count": 2,
"is_parallel": true,
"self": 0.000696809000032772
}
}
},
"UnityEnvironment.step": {
"total": 0.028362722999986545,
"count": 1,
"is_parallel": true,
"self": 0.0003323029999364735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017279500002587156,
"count": 1,
"is_parallel": true,
"self": 0.00017279500002587156
},
"communicator.exchange": {
"total": 0.026984366999954545,
"count": 1,
"is_parallel": true,
"self": 0.026984366999954545
},
"steps_from_proto": {
"total": 0.0008732580000696544,
"count": 1,
"is_parallel": true,
"self": 0.0002116680000199267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006615900000497277,
"count": 2,
"is_parallel": true,
"self": 0.0006615900000497277
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1256.980037385074,
"count": 231625,
"is_parallel": true,
"self": 38.19094698304457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.84581697691135,
"count": 231625,
"is_parallel": true,
"self": 78.84581697691135
},
"communicator.exchange": {
"total": 1052.46373912705,
"count": 231625,
"is_parallel": true,
"self": 1052.46373912705
},
"steps_from_proto": {
"total": 87.47953429806807,
"count": 231625,
"is_parallel": true,
"self": 32.81293625008948,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.666598047978596,
"count": 463250,
"is_parallel": true,
"self": 54.666598047978596
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.040449902064,
"count": 231626,
"self": 6.814309025186958,
"children": {
"process_trajectory": {
"total": 131.81041921387407,
"count": 231626,
"self": 130.1946622318734,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6157569820006756,
"count": 10,
"self": 1.6157569820006756
}
}
},
"_update_policy": {
"total": 379.41572166300296,
"count": 97,
"self": 319.7853613860043,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.63036027699866,
"count": 2910,
"self": 59.63036027699866
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.799996405490674e-07,
"count": 1,
"self": 9.799996405490674e-07
},
"TrainerController._save_models": {
"total": 0.13143710699978328,
"count": 1,
"self": 0.004566535999856569,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1268705709999267,
"count": 1,
"self": 0.1268705709999267
}
}
}
}
}
}
}