ppo-Huggy / run_logs /timers.json
seven-dev's picture
Huggy
592e5a6
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4091312885284424,
"min": 1.4091312885284424,
"max": 1.4277905225753784,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71927.6953125,
"min": 67513.0859375,
"max": 78900.78125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.46911519198665,
"min": 80.57096247960848,
"max": 439.0173913043478,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49399.0,
"min": 48721.0,
"max": 50487.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999959.0,
"min": 49929.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999959.0,
"min": 49929.0,
"max": 1999959.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.405690908432007,
"min": 0.06894857436418533,
"max": 2.473665952682495,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1441.0087890625,
"min": 7.860137462615967,
"max": 1465.8389892578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8011539430172494,
"min": 1.852680847833031,
"max": 3.9504581358252455,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2276.8912118673325,
"min": 211.20561665296555,
"max": 2350.522590816021,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8011539430172494,
"min": 1.852680847833031,
"max": 3.9504581358252455,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2276.8912118673325,
"min": 211.20561665296555,
"max": 2350.522590816021,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.02037306649306427,
"min": 0.013177003317832715,
"max": 0.02037306649306427,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06111919947919281,
"min": 0.02635400663566543,
"max": 0.06111919947919281,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05692051665650474,
"min": 0.021711756568402053,
"max": 0.05863191746175289,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1707615499695142,
"min": 0.04342351313680411,
"max": 0.1707615499695142,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5393988202333443e-06,
"min": 3.5393988202333443e-06,
"max": 0.00029532480155839997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0618196460700033e-05,
"min": 1.0618196460700033e-05,
"max": 0.0008439145686951501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117976666666668,
"min": 0.10117976666666668,
"max": 0.19844159999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353930000000007,
"min": 0.20750415000000005,
"max": 0.5813048500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.887035666666687e-05,
"min": 6.887035666666687e-05,
"max": 0.004922235839999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020661107000000063,
"min": 0.00020661107000000063,
"max": 0.014067112015000001,
"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": "1675597899",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1675600436"
},
"total": 2537.5899411600003,
"count": 1,
"self": 0.4363184370008639,
"children": {
"run_training.setup": {
"total": 0.11473420999982409,
"count": 1,
"self": 0.11473420999982409
},
"TrainerController.start_learning": {
"total": 2537.0388885129996,
"count": 1,
"self": 4.529179977042531,
"children": {
"TrainerController._reset_env": {
"total": 11.31728679600019,
"count": 1,
"self": 11.31728679600019
},
"TrainerController.advance": {
"total": 2521.074879162956,
"count": 232769,
"self": 4.879966653890278,
"children": {
"env_step": {
"total": 1952.7274874128666,
"count": 232769,
"self": 1627.5318818309843,
"children": {
"SubprocessEnvManager._take_step": {
"total": 322.2393717167797,
"count": 232769,
"self": 16.525757306007563,
"children": {
"TorchPolicy.evaluate": {
"total": 305.71361441077215,
"count": 223040,
"self": 75.15425167977901,
"children": {
"TorchPolicy.sample_actions": {
"total": 230.55936273099314,
"count": 223040,
"self": 230.55936273099314
}
}
}
}
},
"workers": {
"total": 2.956233865102604,
"count": 232769,
"self": 0.0,
"children": {
"worker_root": {
"total": 2528.2436119106183,
"count": 232769,
"is_parallel": true,
"self": 1198.5551311773993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021012950001022546,
"count": 1,
"is_parallel": true,
"self": 0.0003655339996839757,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017357610004182789,
"count": 2,
"is_parallel": true,
"self": 0.0017357610004182789
}
}
},
"UnityEnvironment.step": {
"total": 0.04588384699991366,
"count": 1,
"is_parallel": true,
"self": 0.00035683699934452306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019354599999132915,
"count": 1,
"is_parallel": true,
"self": 0.00019354599999132915
},
"communicator.exchange": {
"total": 0.04456722600025387,
"count": 1,
"is_parallel": true,
"self": 0.04456722600025387
},
"steps_from_proto": {
"total": 0.0007662380003239377,
"count": 1,
"is_parallel": true,
"self": 0.000253373000305146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005128650000187918,
"count": 2,
"is_parallel": true,
"self": 0.0005128650000187918
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.688480733219,
"count": 232768,
"is_parallel": true,
"self": 36.48304327693586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.93649590907444,
"count": 232768,
"is_parallel": true,
"self": 77.93649590907444
},
"communicator.exchange": {
"total": 1119.6279572721178,
"count": 232768,
"is_parallel": true,
"self": 1119.6279572721178
},
"steps_from_proto": {
"total": 95.64098427509089,
"count": 232768,
"is_parallel": true,
"self": 38.615080989276066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.02590328581482,
"count": 465536,
"is_parallel": true,
"self": 57.02590328581482
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 563.4674250961993,
"count": 232769,
"self": 7.0360242713359185,
"children": {
"process_trajectory": {
"total": 175.94498421386652,
"count": 232769,
"self": 174.57550735786572,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3694768560008015,
"count": 10,
"self": 1.3694768560008015
}
}
},
"_update_policy": {
"total": 380.4864166109969,
"count": 97,
"self": 321.42637690001584,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.06003971098107,
"count": 2910,
"self": 59.06003971098107
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.170000000973232e-07,
"count": 1,
"self": 8.170000000973232e-07
},
"TrainerController._save_models": {
"total": 0.11754176000067673,
"count": 1,
"self": 0.0022452740004155203,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11529648600026121,
"count": 1,
"self": 0.11529648600026121
}
}
}
}
}
}
}