ppo-Huggy / run_logs /timers.json
eddyyeo's picture
Huggy
872aff4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4074021577835083,
"min": 1.4074021577835083,
"max": 1.4311262369155884,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71011.8828125,
"min": 68882.1640625,
"max": 76442.546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.20445344129554,
"min": 82.26377295492487,
"max": 378.8181818181818,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49501.0,
"min": 48839.0,
"max": 50030.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999960.0,
"min": 49445.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999960.0,
"min": 49445.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4368574619293213,
"min": -0.004850125405937433,
"max": 2.461185932159424,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1203.8076171875,
"min": -0.6353664398193359,
"max": 1436.014892578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7558410596027065,
"min": 1.720105422589615,
"max": 4.010225996282911,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1855.385483443737,
"min": 225.33381035923958,
"max": 2329.1839057803154,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7558410596027065,
"min": 1.720105422589615,
"max": 4.010225996282911,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1855.385483443737,
"min": 225.33381035923958,
"max": 2329.1839057803154,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016193576267768447,
"min": 0.013630878571711946,
"max": 0.020430321245415446,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04858072880330534,
"min": 0.027261757143423892,
"max": 0.05654201250484524,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048089292355709606,
"min": 0.024475376866757867,
"max": 0.056350342060128844,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14426787706712882,
"min": 0.048950753733515734,
"max": 0.16905102618038653,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.809598730166666e-06,
"min": 3.809598730166666e-06,
"max": 0.00029537580154140005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1428796190499999e-05,
"min": 1.1428796190499999e-05,
"max": 0.0008443770185409999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126983333333334,
"min": 0.10126983333333334,
"max": 0.19845860000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038095,
"min": 0.20770275000000002,
"max": 0.5814590000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.336468333333333e-05,
"min": 7.336468333333333e-05,
"max": 0.004923084139999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022009405,
"min": 0.00022009405,
"max": 0.014074804100000003,
"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": "1687541730",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=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": "1687544084"
},
"total": 2354.146539014,
"count": 1,
"self": 0.4419944849996682,
"children": {
"run_training.setup": {
"total": 0.041437577000010606,
"count": 1,
"self": 0.041437577000010606
},
"TrainerController.start_learning": {
"total": 2353.6631069520004,
"count": 1,
"self": 4.266635027827306,
"children": {
"TrainerController._reset_env": {
"total": 4.464949993000005,
"count": 1,
"self": 4.464949993000005
},
"TrainerController.advance": {
"total": 2344.8176132611725,
"count": 232471,
"self": 4.4004503050250605,
"children": {
"env_step": {
"total": 1825.2339020740885,
"count": 232471,
"self": 1535.9771790690677,
"children": {
"SubprocessEnvManager._take_step": {
"total": 286.527101125052,
"count": 232471,
"self": 16.062707175030255,
"children": {
"TorchPolicy.evaluate": {
"total": 270.46439395002176,
"count": 223048,
"self": 270.46439395002176
}
}
},
"workers": {
"total": 2.7296218799688177,
"count": 232471,
"self": 0.0,
"children": {
"worker_root": {
"total": 2346.1242222980427,
"count": 232471,
"is_parallel": true,
"self": 1090.6684760501093,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008860450000156561,
"count": 1,
"is_parallel": true,
"self": 0.00027534499997727835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006107000000383778,
"count": 2,
"is_parallel": true,
"self": 0.0006107000000383778
}
}
},
"UnityEnvironment.step": {
"total": 0.042507767999950374,
"count": 1,
"is_parallel": true,
"self": 0.00032688299984329205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020919000007779687,
"count": 1,
"is_parallel": true,
"self": 0.00020919000007779687
},
"communicator.exchange": {
"total": 0.041259233000005224,
"count": 1,
"is_parallel": true,
"self": 0.041259233000005224
},
"steps_from_proto": {
"total": 0.0007124620000240611,
"count": 1,
"is_parallel": true,
"self": 0.00020616200004042184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005062999999836393,
"count": 2,
"is_parallel": true,
"self": 0.0005062999999836393
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1255.4557462479333,
"count": 232470,
"is_parallel": true,
"self": 38.65031081889674,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.6925373880772,
"count": 232470,
"is_parallel": true,
"self": 77.6925373880772
},
"communicator.exchange": {
"total": 1046.8912870240365,
"count": 232470,
"is_parallel": true,
"self": 1046.8912870240365
},
"steps_from_proto": {
"total": 92.22161101692302,
"count": 232470,
"is_parallel": true,
"self": 32.4931105179063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.72850049901672,
"count": 464940,
"is_parallel": true,
"self": 59.72850049901672
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 515.183260882059,
"count": 232471,
"self": 6.474878604019523,
"children": {
"process_trajectory": {
"total": 134.14996598503967,
"count": 232471,
"self": 132.73867636403907,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4112896210006056,
"count": 10,
"self": 1.4112896210006056
}
}
},
"_update_policy": {
"total": 374.5584162929998,
"count": 97,
"self": 315.81962397401094,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.738792318988885,
"count": 2910,
"self": 58.738792318988885
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.570003385306336e-07,
"count": 1,
"self": 9.570003385306336e-07
},
"TrainerController._save_models": {
"total": 0.11390771300011693,
"count": 1,
"self": 0.001754677000008087,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11215303600010884,
"count": 1,
"self": 0.11215303600010884
}
}
}
}
}
}
}