ppo-Huggy2 / run_logs /timers.json
torreygooch's picture
Huggy
bb71628
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4025322198867798,
"min": 1.4025322198867798,
"max": 1.4275943040847778,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70280.890625,
"min": 68739.875,
"max": 75768.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.32040472175379,
"min": 81.60330578512396,
"max": 387.2403100775194,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49409.0,
"min": 48823.0,
"max": 50087.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999952.0,
"min": 49334.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999952.0,
"min": 49334.0,
"max": 1999952.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4457523822784424,
"min": 0.22500090301036835,
"max": 2.4774115085601807,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1450.3311767578125,
"min": 28.80011558532715,
"max": 1467.5908203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.890695831928446,
"min": 1.7339500519447029,
"max": 3.946328027219307,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2307.1826283335686,
"min": 221.94560664892197,
"max": 2307.1826283335686,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.890695831928446,
"min": 1.7339500519447029,
"max": 3.946328027219307,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2307.1826283335686,
"min": 221.94560664892197,
"max": 2307.1826283335686,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016846310720656118,
"min": 0.012801630986117137,
"max": 0.019514662451304808,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05053893216196835,
"min": 0.025603261972234274,
"max": 0.058324317799027386,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055062368512153625,
"min": 0.01989426414171855,
"max": 0.058355257660150525,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16518710553646088,
"min": 0.0397885282834371,
"max": 0.16902077148358027,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.155798948099994e-06,
"min": 3.155798948099994e-06,
"max": 0.000295298026567325,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.467396844299981e-06,
"min": 9.467396844299981e-06,
"max": 0.0008436075187974999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105189999999999,
"min": 0.10105189999999999,
"max": 0.198432675,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031557,
"min": 0.20726820000000004,
"max": 0.5812025,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.248980999999991e-05,
"min": 6.248980999999991e-05,
"max": 0.004921790482500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018746942999999972,
"min": 0.00018746942999999972,
"max": 0.014062004750000003,
"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": "1685232179",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685234238"
},
"total": 2059.2234815499996,
"count": 1,
"self": 0.32512006999968435,
"children": {
"run_training.setup": {
"total": 0.043138873999964744,
"count": 1,
"self": 0.043138873999964744
},
"TrainerController.start_learning": {
"total": 2058.855222606,
"count": 1,
"self": 4.281889587030946,
"children": {
"TrainerController._reset_env": {
"total": 3.968065849000027,
"count": 1,
"self": 3.968065849000027
},
"TrainerController.advance": {
"total": 2050.4891431329693,
"count": 232501,
"self": 4.111716505968616,
"children": {
"env_step": {
"total": 1587.551557395956,
"count": 232501,
"self": 1320.2632870349498,
"children": {
"SubprocessEnvManager._take_step": {
"total": 264.51694424001016,
"count": 232501,
"self": 15.760913706897782,
"children": {
"TorchPolicy.evaluate": {
"total": 248.75603053311238,
"count": 222948,
"self": 248.75603053311238
}
}
},
"workers": {
"total": 2.7713261209960365,
"count": 232501,
"self": 0.0,
"children": {
"worker_root": {
"total": 2051.081240050006,
"count": 232501,
"is_parallel": true,
"self": 981.5806687050399,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009116539999922679,
"count": 1,
"is_parallel": true,
"self": 0.0002607210000178384,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006509329999744295,
"count": 2,
"is_parallel": true,
"self": 0.0006509329999744295
}
}
},
"UnityEnvironment.step": {
"total": 0.02960260199995446,
"count": 1,
"is_parallel": true,
"self": 0.00035845699994752067,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023049499998251122,
"count": 1,
"is_parallel": true,
"self": 0.00023049499998251122
},
"communicator.exchange": {
"total": 0.02825983799993992,
"count": 1,
"is_parallel": true,
"self": 0.02825983799993992
},
"steps_from_proto": {
"total": 0.0007538120000845083,
"count": 1,
"is_parallel": true,
"self": 0.00019368499999927735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000560127000085231,
"count": 2,
"is_parallel": true,
"self": 0.000560127000085231
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1069.500571344966,
"count": 232500,
"is_parallel": true,
"self": 32.9873415898237,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 62.13660463902352,
"count": 232500,
"is_parallel": true,
"self": 62.13660463902352
},
"communicator.exchange": {
"total": 896.3680689740455,
"count": 232500,
"is_parallel": true,
"self": 896.3680689740455
},
"steps_from_proto": {
"total": 78.0085561420733,
"count": 232500,
"is_parallel": true,
"self": 27.377853418983477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 50.630702723089826,
"count": 465000,
"is_parallel": true,
"self": 50.630702723089826
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 458.82586923104463,
"count": 232501,
"self": 6.5027355480722235,
"children": {
"process_trajectory": {
"total": 121.63851632197418,
"count": 232501,
"self": 120.42057797297446,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2179383489997235,
"count": 10,
"self": 1.2179383489997235
}
}
},
"_update_policy": {
"total": 330.68461736099823,
"count": 97,
"self": 285.2711507399729,
"children": {
"TorchPPOOptimizer.update": {
"total": 45.41346662102535,
"count": 2910,
"self": 45.41346662102535
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.879997039912269e-07,
"count": 1,
"self": 8.879997039912269e-07
},
"TrainerController._save_models": {
"total": 0.11612314900003184,
"count": 1,
"self": 0.0019804529997600184,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11414269600027183,
"count": 1,
"self": 0.11414269600027183
}
}
}
}
}
}
}