ppo-Huggy / run_logs /timers.json
RisiPisi's picture
Huggy
9f911fb
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4003475904464722,
"min": 1.4003475904464722,
"max": 1.4260833263397217,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69903.953125,
"min": 69019.640625,
"max": 76221.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.86027944111777,
"min": 84.0732538330494,
"max": 371.14074074074074,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50030.0,
"min": 48912.0,
"max": 50104.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999751.0,
"min": 49508.0,
"max": 1999751.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999751.0,
"min": 49508.0,
"max": 1999751.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.36033034324646,
"min": 0.032174624502658844,
"max": 2.441969394683838,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1180.1651611328125,
"min": 4.311399459838867,
"max": 1413.4552001953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5853252803087234,
"min": 1.68023146889103,
"max": 3.8966847030462417,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1792.6626401543617,
"min": 225.151016831398,
"max": 2201.6268572211266,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5853252803087234,
"min": 1.68023146889103,
"max": 3.8966847030462417,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1792.6626401543617,
"min": 225.151016831398,
"max": 2201.6268572211266,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01922877371831014,
"min": 0.013008014628333816,
"max": 0.02042360741082424,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05768632115493043,
"min": 0.02601602925666763,
"max": 0.059849324294676376,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05126424936784638,
"min": 0.02360981609672308,
"max": 0.060526009524861965,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15379274810353916,
"min": 0.04721963219344616,
"max": 0.17616509459912777,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2796489068166648e-06,
"min": 3.2796489068166648e-06,
"max": 0.00029534077655307494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.838946720449995e-06,
"min": 9.838946720449995e-06,
"max": 0.0008442525185824998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10109318333333332,
"min": 0.10109318333333332,
"max": 0.19844692499999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30327954999999995,
"min": 0.20735834999999997,
"max": 0.5814174999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.45498483333333e-05,
"min": 6.45498483333333e-05,
"max": 0.0049225015575,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001936495449999999,
"min": 0.0001936495449999999,
"max": 0.014072733249999999,
"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": "1673513230",
"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",
"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": "1673515480"
},
"total": 2250.580000065,
"count": 1,
"self": 0.38908274100003837,
"children": {
"run_training.setup": {
"total": 0.10581935699997302,
"count": 1,
"self": 0.10581935699997302
},
"TrainerController.start_learning": {
"total": 2250.0850979670004,
"count": 1,
"self": 3.965428749021612,
"children": {
"TrainerController._reset_env": {
"total": 7.353980235000108,
"count": 1,
"self": 7.353980235000108
},
"TrainerController.advance": {
"total": 2238.6421365689785,
"count": 232269,
"self": 3.914418219768777,
"children": {
"env_step": {
"total": 1760.4944576001121,
"count": 232269,
"self": 1488.3393698031496,
"children": {
"SubprocessEnvManager._take_step": {
"total": 269.54729876508054,
"count": 232269,
"self": 14.102626759204668,
"children": {
"TorchPolicy.evaluate": {
"total": 255.44467200587587,
"count": 223028,
"self": 64.14767842468973,
"children": {
"TorchPolicy.sample_actions": {
"total": 191.29699358118614,
"count": 223028,
"self": 191.29699358118614
}
}
}
}
},
"workers": {
"total": 2.607789031882021,
"count": 232269,
"self": 0.0,
"children": {
"worker_root": {
"total": 2239.944791356027,
"count": 232269,
"is_parallel": true,
"self": 1012.3838723940178,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002056213999821921,
"count": 1,
"is_parallel": true,
"self": 0.0003250829997796245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017311310000422964,
"count": 2,
"is_parallel": true,
"self": 0.0017311310000422964
}
}
},
"UnityEnvironment.step": {
"total": 0.026830515000028754,
"count": 1,
"is_parallel": true,
"self": 0.0003055560000575497,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001900380000279256,
"count": 1,
"is_parallel": true,
"self": 0.0001900380000279256
},
"communicator.exchange": {
"total": 0.02541121099989141,
"count": 1,
"is_parallel": true,
"self": 0.02541121099989141
},
"steps_from_proto": {
"total": 0.0009237100000518694,
"count": 1,
"is_parallel": true,
"self": 0.0004628750000392756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004608350000125938,
"count": 2,
"is_parallel": true,
"self": 0.0004608350000125938
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1227.5609189620093,
"count": 232268,
"is_parallel": true,
"self": 35.0668061161914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.30770477084457,
"count": 232268,
"is_parallel": true,
"self": 80.30770477084457
},
"communicator.exchange": {
"total": 1011.6435710180319,
"count": 232268,
"is_parallel": true,
"self": 1011.6435710180319
},
"steps_from_proto": {
"total": 100.54283705694138,
"count": 232268,
"is_parallel": true,
"self": 41.18394800378064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.35888905316074,
"count": 464536,
"is_parallel": true,
"self": 59.35888905316074
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.2332607490973,
"count": 232269,
"self": 6.283987698103147,
"children": {
"process_trajectory": {
"total": 150.74396423699704,
"count": 232269,
"self": 149.50950693299706,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2344573039999887,
"count": 10,
"self": 1.2344573039999887
}
}
},
"_update_policy": {
"total": 317.20530881399714,
"count": 97,
"self": 262.9446706289889,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.26063818500825,
"count": 2910,
"self": 54.26063818500825
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.130008038482629e-07,
"count": 1,
"self": 9.130008038482629e-07
},
"TrainerController._save_models": {
"total": 0.12355150099938328,
"count": 1,
"self": 0.002326743999219616,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12122475700016366,
"count": 1,
"self": 0.12122475700016366
}
}
}
}
}
}
}