ppo-Huggy / run_logs /timers.json
sid's picture
Huggy
bd2ea42
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.40309739112854,
"min": 1.40309739112854,
"max": 1.4243799448013306,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68800.8828125,
"min": 68095.5859375,
"max": 79068.84375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.91825095057034,
"min": 80.88707037643208,
"max": 402.264,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49401.0,
"min": 48977.0,
"max": 50283.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999969.0,
"min": 49792.0,
"max": 1999969.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999969.0,
"min": 49792.0,
"max": 1999969.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.34971022605896,
"min": 0.024924730882048607,
"max": 2.4738240242004395,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1235.9476318359375,
"min": 3.0906665325164795,
"max": 1462.005615234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6107517923918966,
"min": 1.8629866936394284,
"max": 3.9789124479388245,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1899.2554427981377,
"min": 231.01035001128912,
"max": 2316.9924871325493,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6107517923918966,
"min": 1.8629866936394284,
"max": 3.9789124479388245,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1899.2554427981377,
"min": 231.01035001128912,
"max": 2316.9924871325493,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017383792994142926,
"min": 0.013333746726534123,
"max": 0.01925113349352614,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052151378982428775,
"min": 0.02853243840509094,
"max": 0.056474140307788426,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05010210416383213,
"min": 0.02387482017899553,
"max": 0.05802086635182301,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1503063124914964,
"min": 0.04774964035799106,
"max": 0.173674326390028,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.574598808500003e-06,
"min": 3.574598808500003e-06,
"max": 0.0002953246515584499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.072379642550001e-05,
"min": 1.072379642550001e-05,
"max": 0.00084413896862035,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119150000000003,
"min": 0.10119150000000003,
"max": 0.19844155000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035745000000001,
"min": 0.20753744999999996,
"max": 0.5813796499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.945585000000004e-05,
"min": 6.945585000000004e-05,
"max": 0.004922233344999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020836755000000013,
"min": 0.00020836755000000013,
"max": 0.014070844534999998,
"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": "1687209498",
"python_version": "3.8.16 (default, Jun 12 2023, 18:09:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/sid/anaconda3/envs/ml_unity_38/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": "1.8.1+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687210786"
},
"total": 1288.1218082809974,
"count": 1,
"self": 0.21761363499535946,
"children": {
"run_training.setup": {
"total": 0.007747823001409415,
"count": 1,
"self": 0.007747823001409415
},
"TrainerController.start_learning": {
"total": 1287.8964468230006,
"count": 1,
"self": 3.243358712657937,
"children": {
"TrainerController._reset_env": {
"total": 2.5523031640004774,
"count": 1,
"self": 2.5523031640004774
},
"TrainerController.advance": {
"total": 1282.034344044343,
"count": 232233,
"self": 3.3966207226949336,
"children": {
"env_step": {
"total": 1001.8301397827272,
"count": 232233,
"self": 789.7409422222408,
"children": {
"SubprocessEnvManager._take_step": {
"total": 209.72801076705218,
"count": 232233,
"self": 9.568885167427652,
"children": {
"TorchPolicy.evaluate": {
"total": 200.15912559962453,
"count": 222930,
"self": 200.15912559962453
}
}
},
"workers": {
"total": 2.3611867934341717,
"count": 232233,
"self": 0.0,
"children": {
"worker_root": {
"total": 1283.816154851007,
"count": 232233,
"is_parallel": true,
"self": 668.0480775830329,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00040999999691848643,
"count": 1,
"is_parallel": true,
"self": 0.0001132769939431455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00029672300297534093,
"count": 2,
"is_parallel": true,
"self": 0.00029672300297534093
}
}
},
"UnityEnvironment.step": {
"total": 0.012794055997801479,
"count": 1,
"is_parallel": true,
"self": 0.00016764899555710144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.294499977841042e-05,
"count": 1,
"is_parallel": true,
"self": 9.294499977841042e-05
},
"communicator.exchange": {
"total": 0.012227864001033595,
"count": 1,
"is_parallel": true,
"self": 0.012227864001033595
},
"steps_from_proto": {
"total": 0.00030559800143237226,
"count": 1,
"is_parallel": true,
"self": 9.669800056144595e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0002089000008709263,
"count": 2,
"is_parallel": true,
"self": 0.0002089000008709263
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 615.7680772679741,
"count": 232232,
"is_parallel": true,
"self": 25.737857543666905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 40.585873387262836,
"count": 232232,
"is_parallel": true,
"self": 40.585873387262836
},
"communicator.exchange": {
"total": 491.857572063127,
"count": 232232,
"is_parallel": true,
"self": 491.857572063127
},
"steps_from_proto": {
"total": 57.5867742739174,
"count": 232232,
"is_parallel": true,
"self": 19.866545817421866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.72022845649553,
"count": 464464,
"is_parallel": true,
"self": 37.72022845649553
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 276.8075835389209,
"count": 232233,
"self": 4.482119963558944,
"children": {
"process_trajectory": {
"total": 90.93177184836895,
"count": 232233,
"self": 90.20850331437032,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7232685339986347,
"count": 10,
"self": 0.7232685339986347
}
}
},
"_update_policy": {
"total": 181.39369172699298,
"count": 97,
"self": 153.58463905405006,
"children": {
"TorchPPOOptimizer.update": {
"total": 27.809052672942926,
"count": 2910,
"self": 27.809052672942926
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.350011633709073e-07,
"count": 1,
"self": 5.350011633709073e-07
},
"TrainerController._save_models": {
"total": 0.06644036699799472,
"count": 1,
"self": 0.0012903179958811961,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06515004900211352,
"count": 1,
"self": 0.06515004900211352
}
}
}
}
}
}
}