ppo-Huggy / run_logs /timers.json
jfelgate's picture
Huggy
5eae1c0
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4049382209777832,
"min": 1.4049382209777832,
"max": 1.4275778532028198,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68806.8515625,
"min": 68408.8125,
"max": 77744.8671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.75641025641026,
"min": 85.56401384083046,
"max": 405.7479674796748,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49494.0,
"min": 48764.0,
"max": 50228.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49731.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49731.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4029605388641357,
"min": 0.12944379448890686,
"max": 2.4845385551452637,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1126.988525390625,
"min": 15.792142868041992,
"max": 1393.595458984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6217512232916698,
"min": 1.8385749156357811,
"max": 3.9695676155664303,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1698.601323723793,
"min": 224.3061397075653,
"max": 2164.365445435047,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6217512232916698,
"min": 1.8385749156357811,
"max": 3.9695676155664303,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1698.601323723793,
"min": 224.3061397075653,
"max": 2164.365445435047,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01679981731552592,
"min": 0.013001874040734643,
"max": 0.01918557339037458,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05039945194657776,
"min": 0.030186657901261543,
"max": 0.055116832167065394,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.044089709056748284,
"min": 0.02179198128481706,
"max": 0.05819892461101214,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13226912717024486,
"min": 0.04358396256963412,
"max": 0.1724345499028762,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.64609878466666e-06,
"min": 3.64609878466666e-06,
"max": 0.00029531917656027497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.093829635399998e-05,
"min": 1.093829635399998e-05,
"max": 0.0008438875687041497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121533333333334,
"min": 0.10121533333333334,
"max": 0.198439725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.303646,
"min": 0.2075788500000001,
"max": 0.5812958500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.064513333333324e-05,
"min": 7.064513333333324e-05,
"max": 0.0049221422774999996,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002119353999999997,
"min": 0.0002119353999999997,
"max": 0.014066662915,
"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": "1693654376",
"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": "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": "1693657618"
},
"total": 3241.948878886,
"count": 1,
"self": 0.4906840110002122,
"children": {
"run_training.setup": {
"total": 0.04910454799983199,
"count": 1,
"self": 0.04910454799983199
},
"TrainerController.start_learning": {
"total": 3241.409090327,
"count": 1,
"self": 7.455073068153979,
"children": {
"TrainerController._reset_env": {
"total": 5.398053542000071,
"count": 1,
"self": 5.398053542000071
},
"TrainerController.advance": {
"total": 3228.4140595648464,
"count": 232276,
"self": 6.953680952897685,
"children": {
"env_step": {
"total": 2576.0547060990525,
"count": 232276,
"self": 2159.376237398089,
"children": {
"SubprocessEnvManager._take_step": {
"total": 412.16534666602547,
"count": 232276,
"self": 23.663879631081045,
"children": {
"TorchPolicy.evaluate": {
"total": 388.5014670349444,
"count": 222976,
"self": 388.5014670349444
}
}
},
"workers": {
"total": 4.513122034938078,
"count": 232276,
"self": 0.0,
"children": {
"worker_root": {
"total": 3230.3382947669074,
"count": 232276,
"is_parallel": true,
"self": 1486.5419406709937,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001104562999898917,
"count": 1,
"is_parallel": true,
"self": 0.0003103620001638774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007942009997350397,
"count": 2,
"is_parallel": true,
"self": 0.0007942009997350397
}
}
},
"UnityEnvironment.step": {
"total": 0.07422460099996897,
"count": 1,
"is_parallel": true,
"self": 0.00042496599985497596,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002456229999552306,
"count": 1,
"is_parallel": true,
"self": 0.0002456229999552306
},
"communicator.exchange": {
"total": 0.07271220100005849,
"count": 1,
"is_parallel": true,
"self": 0.07271220100005849
},
"steps_from_proto": {
"total": 0.0008418110001002788,
"count": 1,
"is_parallel": true,
"self": 0.00024343300015061686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005983779999496619,
"count": 2,
"is_parallel": true,
"self": 0.0005983779999496619
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1743.7963540959138,
"count": 232275,
"is_parallel": true,
"self": 51.21792199299739,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 105.59900911493492,
"count": 232275,
"is_parallel": true,
"self": 105.59900911493492
},
"communicator.exchange": {
"total": 1455.8626942719995,
"count": 232275,
"is_parallel": true,
"self": 1455.8626942719995
},
"steps_from_proto": {
"total": 131.11672871598194,
"count": 232275,
"is_parallel": true,
"self": 48.14232287889581,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.97440583708612,
"count": 464550,
"is_parallel": true,
"self": 82.97440583708612
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 645.405672512896,
"count": 232276,
"self": 10.507044023872368,
"children": {
"process_trajectory": {
"total": 185.11947779102388,
"count": 232276,
"self": 183.45884021802385,
"children": {
"RLTrainer._checkpoint": {
"total": 1.660637573000031,
"count": 10,
"self": 1.660637573000031
}
}
},
"_update_policy": {
"total": 449.77915069799974,
"count": 97,
"self": 385.8190678129895,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.96008288501025,
"count": 2910,
"self": 63.96008288501025
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2169994079158641e-06,
"count": 1,
"self": 1.2169994079158641e-06
},
"TrainerController._save_models": {
"total": 0.14190293499996187,
"count": 1,
"self": 0.002324736000446137,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13957819899951573,
"count": 1,
"self": 0.13957819899951573
}
}
}
}
}
}
}