ppo-Huggy / run_logs /timers.json
Andrei Mitrofan
Huggy
76ab6ec
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066708087921143,
"min": 1.4066708087921143,
"max": 1.4320334196090698,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70861.0390625,
"min": 68928.6328125,
"max": 75382.0234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.53670473083197,
"min": 80.3479674796748,
"max": 393.75396825396825,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49369.0,
"min": 49042.0,
"max": 50236.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49986.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49986.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4835824966430664,
"min": 0.005519932135939598,
"max": 2.4968693256378174,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1522.43603515625,
"min": 0.6899915337562561,
"max": 1522.43603515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8151878223528093,
"min": 1.7963060657978058,
"max": 3.974545169429681,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2338.710135102272,
"min": 224.53825822472572,
"max": 2352.022219657898,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8151878223528093,
"min": 1.7963060657978058,
"max": 3.974545169429681,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2338.710135102272,
"min": 224.53825822472572,
"max": 2352.022219657898,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01379888583420931,
"min": 0.013464466259271526,
"max": 0.020022278647714605,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.02759777166841862,
"min": 0.02692893251854305,
"max": 0.05997894546114064,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05788745749741793,
"min": 0.020992445386946203,
"max": 0.06574861289312442,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11577491499483586,
"min": 0.041984890773892405,
"max": 0.19518075523277123,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.555748481450006e-06,
"min": 4.555748481450006e-06,
"max": 0.000295236376587875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.111496962900012e-06,
"min": 9.111496962900012e-06,
"max": 0.00084355756881415,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10151855,
"min": 0.10151855,
"max": 0.1984121250000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2030371,
"min": 0.2030371,
"max": 0.5811858500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.577564500000008e-05,
"min": 8.577564500000008e-05,
"max": 0.004920765037500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017155129000000015,
"min": 0.00017155129000000015,
"max": 0.014061173915,
"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": "1672136600",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --resume",
"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": "1672138825"
},
"total": 2225.444037756,
"count": 1,
"self": 0.373903846000303,
"children": {
"run_training.setup": {
"total": 0.10835587099995792,
"count": 1,
"self": 0.10835587099995792
},
"TrainerController.start_learning": {
"total": 2224.961778039,
"count": 1,
"self": 3.8988479209237994,
"children": {
"TrainerController._reset_env": {
"total": 6.374010347000024,
"count": 1,
"self": 6.374010347000024
},
"TrainerController.advance": {
"total": 2214.569802326076,
"count": 232300,
"self": 4.179939088025549,
"children": {
"env_step": {
"total": 1741.8461181699931,
"count": 232300,
"self": 1463.244573808024,
"children": {
"SubprocessEnvManager._take_step": {
"total": 276.00289657995546,
"count": 232300,
"self": 13.987330417951284,
"children": {
"TorchPolicy.evaluate": {
"total": 262.0155661620042,
"count": 222898,
"self": 65.25599957393553,
"children": {
"TorchPolicy.sample_actions": {
"total": 196.75956658806865,
"count": 222898,
"self": 196.75956658806865
}
}
}
}
},
"workers": {
"total": 2.5986477820137566,
"count": 232300,
"self": 0.0,
"children": {
"worker_root": {
"total": 2217.315665908051,
"count": 232300,
"is_parallel": true,
"self": 1008.658252225988,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010851279999997132,
"count": 1,
"is_parallel": true,
"self": 0.0003006439999921895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007844840000075237,
"count": 2,
"is_parallel": true,
"self": 0.0007844840000075237
}
}
},
"UnityEnvironment.step": {
"total": 0.028261290000045847,
"count": 1,
"is_parallel": true,
"self": 0.0002680710000504405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00017687600001181636,
"count": 1,
"is_parallel": true,
"self": 0.00017687600001181636
},
"communicator.exchange": {
"total": 0.027019768000002387,
"count": 1,
"is_parallel": true,
"self": 0.027019768000002387
},
"steps_from_proto": {
"total": 0.0007965749999812033,
"count": 1,
"is_parallel": true,
"self": 0.0002571589999433854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005394160000378179,
"count": 2,
"is_parallel": true,
"self": 0.0005394160000378179
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1208.657413682063,
"count": 232299,
"is_parallel": true,
"self": 34.85275116805224,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.11048699299465,
"count": 232299,
"is_parallel": true,
"self": 76.11048699299465
},
"communicator.exchange": {
"total": 1004.4572747820005,
"count": 232299,
"is_parallel": true,
"self": 1004.4572747820005
},
"steps_from_proto": {
"total": 93.23690073901543,
"count": 232299,
"is_parallel": true,
"self": 38.20979004006546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.02711069894997,
"count": 464598,
"is_parallel": true,
"self": 55.02711069894997
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 468.54374506805755,
"count": 232300,
"self": 6.064972233011815,
"children": {
"process_trajectory": {
"total": 148.4625698990444,
"count": 232300,
"self": 147.27092911804448,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1916407809999328,
"count": 10,
"self": 1.1916407809999328
}
}
},
"_update_policy": {
"total": 314.0162029360013,
"count": 96,
"self": 261.0455596830022,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.97064325299914,
"count": 2880,
"self": 52.97064325299914
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1160000212839805e-06,
"count": 1,
"self": 1.1160000212839805e-06
},
"TrainerController._save_models": {
"total": 0.11911632900000768,
"count": 1,
"self": 0.003175844999987021,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11594048400002066,
"count": 1,
"self": 0.11594048400002066
}
}
}
}
}
}
}