ppo-Huggy / run_logs /timers.json
lukaszkolodziejczyk's picture
Huggy
662fec4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401006817817688,
"min": 1.401006817817688,
"max": 1.426987648010254,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68813.25,
"min": 68813.25,
"max": 78108.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.59122807017543,
"min": 85.07504363001745,
"max": 372.6740740740741,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49357.0,
"min": 48748.0,
"max": 50311.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999923.0,
"min": 49871.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999923.0,
"min": 49871.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.378376007080078,
"min": -0.04965152218937874,
"max": 2.41062593460083,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1355.67431640625,
"min": -6.653304100036621,
"max": 1357.231201171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.763979846866507,
"min": 1.7389433421750566,
"max": 3.9393235164259393,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2145.468512713909,
"min": 233.0184078514576,
"max": 2194.8324279785156,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.763979846866507,
"min": 1.7389433421750566,
"max": 3.9393235164259393,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2145.468512713909,
"min": 233.0184078514576,
"max": 2194.8324279785156,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016978024273218276,
"min": 0.0132997733809235,
"max": 0.0199926129799375,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05093407281965483,
"min": 0.027313628773360202,
"max": 0.055507473569984235,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054816763475537295,
"min": 0.0239273433573544,
"max": 0.06234530583024025,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16445029042661188,
"min": 0.0478546867147088,
"max": 0.18096040847400824,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3284488905500017e-06,
"min": 3.3284488905500017e-06,
"max": 0.0002953053765648749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.985346671650005e-06,
"min": 9.985346671650005e-06,
"max": 0.0008439399186866999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110944999999999,
"min": 0.10110944999999999,
"max": 0.19843512500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30332834999999997,
"min": 0.20740034999999998,
"max": 0.5813133000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.536155500000005e-05,
"min": 6.536155500000005e-05,
"max": 0.004921912737500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019608466500000015,
"min": 0.00019608466500000015,
"max": 0.01406753367,
"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": "1687938580",
"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": "1687941374"
},
"total": 2793.966428419,
"count": 1,
"self": 0.435838461000003,
"children": {
"run_training.setup": {
"total": 0.051430693999975574,
"count": 1,
"self": 0.051430693999975574
},
"TrainerController.start_learning": {
"total": 2793.479159264,
"count": 1,
"self": 5.565683366934991,
"children": {
"TrainerController._reset_env": {
"total": 5.685761188000015,
"count": 1,
"self": 5.685761188000015
},
"TrainerController.advance": {
"total": 2782.103196354065,
"count": 231675,
"self": 5.715782213123475,
"children": {
"env_step": {
"total": 2194.783593559018,
"count": 231675,
"self": 1848.9328430470232,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.233912494076,
"count": 231675,
"self": 19.80046238004104,
"children": {
"TorchPolicy.evaluate": {
"total": 322.43345011403494,
"count": 222786,
"self": 322.43345011403494
}
}
},
"workers": {
"total": 3.61683801791861,
"count": 231675,
"self": 0.0,
"children": {
"worker_root": {
"total": 2784.0315755910556,
"count": 231675,
"is_parallel": true,
"self": 1283.514339796132,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00133969299997716,
"count": 1,
"is_parallel": true,
"self": 0.0003370449999806624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010026479999964977,
"count": 2,
"is_parallel": true,
"self": 0.0010026479999964977
}
}
},
"UnityEnvironment.step": {
"total": 0.030156164999993962,
"count": 1,
"is_parallel": true,
"self": 0.00035429100000783365,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025557399999343033,
"count": 1,
"is_parallel": true,
"self": 0.00025557399999343033
},
"communicator.exchange": {
"total": 0.02885047699999177,
"count": 1,
"is_parallel": true,
"self": 0.02885047699999177
},
"steps_from_proto": {
"total": 0.000695823000000928,
"count": 1,
"is_parallel": true,
"self": 0.00019568499999422784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005001380000067002,
"count": 2,
"is_parallel": true,
"self": 0.0005001380000067002
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1500.5172357949236,
"count": 231674,
"is_parallel": true,
"self": 44.08857280974917,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.49316842901453,
"count": 231674,
"is_parallel": true,
"self": 90.49316842901453
},
"communicator.exchange": {
"total": 1256.9907736630787,
"count": 231674,
"is_parallel": true,
"self": 1256.9907736630787
},
"steps_from_proto": {
"total": 108.94472089308118,
"count": 231674,
"is_parallel": true,
"self": 40.52537444005753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.41934645302365,
"count": 463348,
"is_parallel": true,
"self": 68.41934645302365
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 581.6038205819239,
"count": 231675,
"self": 8.691549538979416,
"children": {
"process_trajectory": {
"total": 152.51871953694524,
"count": 231675,
"self": 150.95328143894585,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5654380979993903,
"count": 10,
"self": 1.5654380979993903
}
}
},
"_update_policy": {
"total": 420.39355150599926,
"count": 97,
"self": 355.73665817298644,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.65689333301282,
"count": 2910,
"self": 64.65689333301282
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0660000953066628e-06,
"count": 1,
"self": 1.0660000953066628e-06
},
"TrainerController._save_models": {
"total": 0.12451728899986847,
"count": 1,
"self": 0.002036995999787905,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12248029300008056,
"count": 1,
"self": 0.12248029300008056
}
}
}
}
}
}
}