ppo-Huggy / run_logs /timers.json
DTorregrosa's picture
Huggy
bb27e8e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4062961339950562,
"min": 1.4062961339950562,
"max": 1.4274823665618896,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68607.5625,
"min": 68607.5625,
"max": 78532.5234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 126.15167095115682,
"min": 75.45871559633028,
"max": 382.69465648854964,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49073.0,
"min": 48940.0,
"max": 50133.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49941.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49941.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2283294200897217,
"min": 0.06362658739089966,
"max": 2.48148250579834,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 866.8201904296875,
"min": 8.271456718444824,
"max": 1592.4105224609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.1230351756348402,
"min": 1.9063197495845647,
"max": 4.011351564937819,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1214.8606833219528,
"min": 247.82156744599342,
"max": 2574.494201004505,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.1230351756348402,
"min": 1.9063197495845647,
"max": 4.011351564937819,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1214.8606833219528,
"min": 247.82156744599342,
"max": 2574.494201004505,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016935769194969908,
"min": 0.013729492857843677,
"max": 0.02010725283988803,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05080730758490973,
"min": 0.027458985715687355,
"max": 0.06032175851966409,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04325639713141654,
"min": 0.022646856680512428,
"max": 0.06031745440430111,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1297691913942496,
"min": 0.045293713361024855,
"max": 0.18095236321290334,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.401298866266659e-06,
"min": 3.401298866266659e-06,
"max": 0.00029531077656307504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0203896598799977e-05,
"min": 1.0203896598799977e-05,
"max": 0.0008440429686523502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113373333333335,
"min": 0.10113373333333335,
"max": 0.19843692499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30340120000000004,
"min": 0.20744220000000002,
"max": 0.5813476500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.657329333333322e-05,
"min": 6.657329333333322e-05,
"max": 0.004922002557499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019971987999999969,
"min": 0.00019971987999999969,
"max": 0.014069247734999998,
"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": "1681723269",
"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=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": "1681725704"
},
"total": 2434.968390838,
"count": 1,
"self": 0.3971315309995589,
"children": {
"run_training.setup": {
"total": 0.11119371899997077,
"count": 1,
"self": 0.11119371899997077
},
"TrainerController.start_learning": {
"total": 2434.4600655880004,
"count": 1,
"self": 4.480457885008491,
"children": {
"TrainerController._reset_env": {
"total": 3.8511621069999933,
"count": 1,
"self": 3.8511621069999933
},
"TrainerController.advance": {
"total": 2425.997838797992,
"count": 232376,
"self": 4.730530157917201,
"children": {
"env_step": {
"total": 1907.2506377070408,
"count": 232376,
"self": 1615.3862189540828,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.8712250779777,
"count": 232376,
"self": 17.160593689937173,
"children": {
"TorchPolicy.evaluate": {
"total": 271.71063138804055,
"count": 223106,
"self": 271.71063138804055
}
}
},
"workers": {
"total": 2.9931936749803185,
"count": 232376,
"self": 0.0,
"children": {
"worker_root": {
"total": 2426.2061144620075,
"count": 232376,
"is_parallel": true,
"self": 1104.0485081441432,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009144879999780642,
"count": 1,
"is_parallel": true,
"self": 0.0002830569999900945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006314309999879697,
"count": 2,
"is_parallel": true,
"self": 0.0006314309999879697
}
}
},
"UnityEnvironment.step": {
"total": 0.03208973699997841,
"count": 1,
"is_parallel": true,
"self": 0.00035268999994286787,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021664000001919703,
"count": 1,
"is_parallel": true,
"self": 0.00021664000001919703
},
"communicator.exchange": {
"total": 0.030775648000030742,
"count": 1,
"is_parallel": true,
"self": 0.030775648000030742
},
"steps_from_proto": {
"total": 0.0007447589999856064,
"count": 1,
"is_parallel": true,
"self": 0.000238856000009946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005059029999756604,
"count": 2,
"is_parallel": true,
"self": 0.0005059029999756604
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1322.1576063178643,
"count": 232375,
"is_parallel": true,
"self": 39.09575837476427,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.45405460206229,
"count": 232375,
"is_parallel": true,
"self": 85.45405460206229
},
"communicator.exchange": {
"total": 1105.9482049009096,
"count": 232375,
"is_parallel": true,
"self": 1105.9482049009096
},
"steps_from_proto": {
"total": 91.65958844012812,
"count": 232375,
"is_parallel": true,
"self": 36.72429152403686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.93529691609126,
"count": 464750,
"is_parallel": true,
"self": 54.93529691609126
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 514.0166709330338,
"count": 232376,
"self": 6.978089905041031,
"children": {
"process_trajectory": {
"total": 137.0076872009916,
"count": 232376,
"self": 135.55655342099084,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4511337800007595,
"count": 10,
"self": 1.4511337800007595
}
}
},
"_update_policy": {
"total": 370.03089382700114,
"count": 97,
"self": 310.8044786369888,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.22641519001235,
"count": 2910,
"self": 59.22641519001235
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.059999683813658e-07,
"count": 1,
"self": 9.059999683813658e-07
},
"TrainerController._save_models": {
"total": 0.13060589199994865,
"count": 1,
"self": 0.002137920000222948,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1284679719997257,
"count": 1,
"self": 0.1284679719997257
}
}
}
}
}
}
}