ppo-Huggy / run_logs /timers.json
joeyzero's picture
Huggy
4120fba
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4022201299667358,
"min": 1.4022201299667358,
"max": 1.4281854629516602,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68340.0,
"min": 67716.203125,
"max": 78590.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.57142857142857,
"min": 96.8082191780822,
"max": 417.34166666666664,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49513.0,
"min": 49048.0,
"max": 50309.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999942.0,
"min": 49452.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999942.0,
"min": 49452.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.311706781387329,
"min": 0.05950600653886795,
"max": 2.3981001377105713,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1084.1904296875,
"min": 7.081214904785156,
"max": 1202.41064453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.533846143720501,
"min": 1.7376161619645207,
"max": 3.7991696752053152,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1657.3738414049149,
"min": 206.77632327377796,
"max": 1888.3071684837341,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.533846143720501,
"min": 1.7376161619645207,
"max": 3.7991696752053152,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1657.3738414049149,
"min": 206.77632327377796,
"max": 1888.3071684837341,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018179520794850156,
"min": 0.013782965223981591,
"max": 0.019203684139453496,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03635904158970031,
"min": 0.027565930447963183,
"max": 0.05676959257101165,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05431505329906941,
"min": 0.020395390472064415,
"max": 0.06714881863445044,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10863010659813882,
"min": 0.04079078094412883,
"max": 0.1956405178954204,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.366598544499995e-06,
"min": 4.366598544499995e-06,
"max": 0.00029531782656072494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.73319708899999e-06,
"min": 8.73319708899999e-06,
"max": 0.0008438446687184498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10145550000000003,
"min": 0.10145550000000003,
"max": 0.19843927499999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20291100000000006,
"min": 0.20291100000000006,
"max": 0.58128155,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.262944999999992e-05,
"min": 8.262944999999992e-05,
"max": 0.0049221198224999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016525889999999984,
"min": 0.00016525889999999984,
"max": 0.014065949345,
"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": "1701083814",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701086281"
},
"total": 2466.4189084199998,
"count": 1,
"self": 0.4437202649992287,
"children": {
"run_training.setup": {
"total": 0.05873585000000503,
"count": 1,
"self": 0.05873585000000503
},
"TrainerController.start_learning": {
"total": 2465.9164523050003,
"count": 1,
"self": 4.575711382984991,
"children": {
"TrainerController._reset_env": {
"total": 3.5826813650000418,
"count": 1,
"self": 3.5826813650000418
},
"TrainerController.advance": {
"total": 2457.652372971015,
"count": 230542,
"self": 4.851149649057334,
"children": {
"env_step": {
"total": 1949.3227358869876,
"count": 230542,
"self": 1603.9982091459394,
"children": {
"SubprocessEnvManager._take_step": {
"total": 342.4555677700471,
"count": 230542,
"self": 17.75886805599788,
"children": {
"TorchPolicy.evaluate": {
"total": 324.6966997140492,
"count": 222756,
"self": 324.6966997140492
}
}
},
"workers": {
"total": 2.8689589710010637,
"count": 230542,
"self": 0.0,
"children": {
"worker_root": {
"total": 2458.4994212150687,
"count": 230542,
"is_parallel": true,
"self": 1161.7384204791188,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000807990999987851,
"count": 1,
"is_parallel": true,
"self": 0.00021672300005093348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005912679999369175,
"count": 2,
"is_parallel": true,
"self": 0.0005912679999369175
}
}
},
"UnityEnvironment.step": {
"total": 0.03097283299996434,
"count": 1,
"is_parallel": true,
"self": 0.0003343319999657979,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002048549999926763,
"count": 1,
"is_parallel": true,
"self": 0.0002048549999926763
},
"communicator.exchange": {
"total": 0.02968403400001307,
"count": 1,
"is_parallel": true,
"self": 0.02968403400001307
},
"steps_from_proto": {
"total": 0.0007496119999927942,
"count": 1,
"is_parallel": true,
"self": 0.0002000049999537623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005496070000390318,
"count": 2,
"is_parallel": true,
"self": 0.0005496070000390318
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1296.76100073595,
"count": 230541,
"is_parallel": true,
"self": 40.2809909369862,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.95763765097627,
"count": 230541,
"is_parallel": true,
"self": 81.95763765097627
},
"communicator.exchange": {
"total": 1085.1645610589621,
"count": 230541,
"is_parallel": true,
"self": 1085.1645610589621
},
"steps_from_proto": {
"total": 89.3578110890254,
"count": 230541,
"is_parallel": true,
"self": 31.163148504984065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.19466258404134,
"count": 461082,
"is_parallel": true,
"self": 58.19466258404134
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.47848743497013,
"count": 230542,
"self": 6.895363077960724,
"children": {
"process_trajectory": {
"total": 151.0611072380085,
"count": 230542,
"self": 149.8096856720092,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2514215659992942,
"count": 10,
"self": 1.2514215659992942
}
}
},
"_update_policy": {
"total": 345.5220171190009,
"count": 96,
"self": 282.24253100700724,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.27948611199366,
"count": 2880,
"self": 63.27948611199366
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.03899992609513e-06,
"count": 1,
"self": 1.03899992609513e-06
},
"TrainerController._save_models": {
"total": 0.105685547000121,
"count": 1,
"self": 0.0016541000004508533,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10403144699967015,
"count": 1,
"self": 0.10403144699967015
}
}
}
}
}
}
}