ppo-Huggy / run_logs /timers.json
eswat's picture
Initial commit
7f1e95b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3992969989776611,
"min": 1.3992969989776611,
"max": 1.4242907762527466,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70370.6484375,
"min": 68515.40625,
"max": 76685.3515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.8590831918506,
"min": 79.83656957928802,
"max": 375.4812030075188,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49393.0,
"min": 48986.0,
"max": 50081.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999955.0,
"min": 49387.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999955.0,
"min": 49387.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4577605724334717,
"min": 0.06662692129611969,
"max": 2.4577605724334717,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1447.6209716796875,
"min": 8.794754028320312,
"max": 1488.321044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8256904377597296,
"min": 1.9182734940991257,
"max": 3.9274505122287855,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2253.331667840481,
"min": 253.2121012210846,
"max": 2384.811146914959,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8256904377597296,
"min": 1.9182734940991257,
"max": 3.9274505122287855,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2253.331667840481,
"min": 253.2121012210846,
"max": 2384.811146914959,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01593965366773773,
"min": 0.011911129245481787,
"max": 0.02032759214635007,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047818961003213194,
"min": 0.023822258490963574,
"max": 0.057797856240843735,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05429686009883881,
"min": 0.022238673021396003,
"max": 0.05892858039587736,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16289058029651643,
"min": 0.04447734604279201,
"max": 0.17662177768846354,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4538988487333287e-06,
"min": 3.4538988487333287e-06,
"max": 0.0002953563015479,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0361696546199986e-05,
"min": 1.0361696546199986e-05,
"max": 0.0008440246686584499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115126666666668,
"min": 0.10115126666666668,
"max": 0.19845209999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30345380000000005,
"min": 0.20745035000000006,
"max": 0.5813415499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.744820666666662e-05,
"min": 6.744820666666662e-05,
"max": 0.004922759789999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020234461999999985,
"min": 0.00020234461999999985,
"max": 0.014068943345,
"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": "1680651493",
"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": "1680653900"
},
"total": 2407.7612935469997,
"count": 1,
"self": 0.4332057969991183,
"children": {
"run_training.setup": {
"total": 0.18635346999997182,
"count": 1,
"self": 0.18635346999997182
},
"TrainerController.start_learning": {
"total": 2407.1417342800005,
"count": 1,
"self": 4.451741761041831,
"children": {
"TrainerController._reset_env": {
"total": 3.7765241399999923,
"count": 1,
"self": 3.7765241399999923
},
"TrainerController.advance": {
"total": 2398.7875439689587,
"count": 232456,
"self": 4.784485867016883,
"children": {
"env_step": {
"total": 1890.0795188289815,
"count": 232456,
"self": 1604.450620663057,
"children": {
"SubprocessEnvManager._take_step": {
"total": 282.6885908819394,
"count": 232456,
"self": 17.24593509190413,
"children": {
"TorchPolicy.evaluate": {
"total": 265.44265579003525,
"count": 222895,
"self": 265.44265579003525
}
}
},
"workers": {
"total": 2.9403072839851347,
"count": 232456,
"self": 0.0,
"children": {
"worker_root": {
"total": 2398.865089807966,
"count": 232456,
"is_parallel": true,
"self": 1086.706429697896,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009252779999542327,
"count": 1,
"is_parallel": true,
"self": 0.00027266399979453126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006526140001597014,
"count": 2,
"is_parallel": true,
"self": 0.0006526140001597014
}
}
},
"UnityEnvironment.step": {
"total": 0.03032797200000914,
"count": 1,
"is_parallel": true,
"self": 0.00028145200008111715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026629900003172224,
"count": 1,
"is_parallel": true,
"self": 0.00026629900003172224
},
"communicator.exchange": {
"total": 0.02908495299993774,
"count": 1,
"is_parallel": true,
"self": 0.02908495299993774
},
"steps_from_proto": {
"total": 0.0006952679999585598,
"count": 1,
"is_parallel": true,
"self": 0.00023875399983808165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045651400012047816,
"count": 2,
"is_parallel": true,
"self": 0.00045651400012047816
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1312.1586601100698,
"count": 232455,
"is_parallel": true,
"self": 37.757195391003734,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.07244270204114,
"count": 232455,
"is_parallel": true,
"self": 84.07244270204114
},
"communicator.exchange": {
"total": 1099.4209733479483,
"count": 232455,
"is_parallel": true,
"self": 1099.4209733479483
},
"steps_from_proto": {
"total": 90.90804866907649,
"count": 232455,
"is_parallel": true,
"self": 36.285096718037266,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.62295195103923,
"count": 464910,
"is_parallel": true,
"self": 54.62295195103923
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.9235392729606,
"count": 232456,
"self": 6.822649691993661,
"children": {
"process_trajectory": {
"total": 135.50091490196826,
"count": 232456,
"self": 134.01048685096862,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4904280509996397,
"count": 10,
"self": 1.4904280509996397
}
}
},
"_update_policy": {
"total": 361.5999746789987,
"count": 97,
"self": 303.7055694119995,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.89440526699923,
"count": 2910,
"self": 57.89440526699923
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1419997463235632e-06,
"count": 1,
"self": 1.1419997463235632e-06
},
"TrainerController._save_models": {
"total": 0.12592326799995135,
"count": 1,
"self": 0.002119903999755479,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12380336400019587,
"count": 1,
"self": 0.12380336400019587
}
}
}
}
}
}
}