ppo-Huggy / run_logs /timers.json
ambihan's picture
Huggy
cd3be35
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4061381816864014,
"min": 1.4061381816864014,
"max": 1.4315015077590942,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71357.296875,
"min": 68061.7734375,
"max": 76954.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.2852897473997,
"min": 71.25396825396825,
"max": 391.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49321.0,
"min": 49199.0,
"max": 50108.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999867.0,
"min": 49487.0,
"max": 1999867.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999867.0,
"min": 49487.0,
"max": 1999867.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4898314476013184,
"min": 0.12616023421287537,
"max": 2.4898314476013184,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1675.6566162109375,
"min": 16.022350311279297,
"max": 1708.7509765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9604763696841996,
"min": 1.7749018662088498,
"max": 3.980285690890418,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2665.4005967974663,
"min": 225.41253700852394,
"max": 2670.33096909523,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9604763696841996,
"min": 1.7749018662088498,
"max": 3.980285690890418,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2665.4005967974663,
"min": 225.41253700852394,
"max": 2670.33096909523,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016963447095865072,
"min": 0.01329074363239897,
"max": 0.020585372527663518,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05089034128759522,
"min": 0.02658148726479794,
"max": 0.05718156626971904,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0640257767919037,
"min": 0.0217575383062164,
"max": 0.0640257767919037,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19207733037571112,
"min": 0.0435150766124328,
"max": 0.19207733037571112,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.647848784083328e-06,
"min": 3.647848784083328e-06,
"max": 0.0002953108515630499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0943546352249985e-05,
"min": 1.0943546352249985e-05,
"max": 0.0008437213687595499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121591666666668,
"min": 0.10121591666666668,
"max": 0.19843695000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364775000000005,
"min": 0.2075912,
"max": 0.5812404500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.067424166666656e-05,
"min": 7.067424166666656e-05,
"max": 0.004922003804999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021202272499999968,
"min": 0.00021202272499999968,
"max": 0.014063898454999998,
"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": "1687527556",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687530002"
},
"total": 2446.236677686,
"count": 1,
"self": 0.4380953130003036,
"children": {
"run_training.setup": {
"total": 0.04324794399985876,
"count": 1,
"self": 0.04324794399985876
},
"TrainerController.start_learning": {
"total": 2445.755334429,
"count": 1,
"self": 4.60908239508808,
"children": {
"TrainerController._reset_env": {
"total": 5.582254271000011,
"count": 1,
"self": 5.582254271000011
},
"TrainerController.advance": {
"total": 2435.4494454659116,
"count": 232883,
"self": 4.546669038827076,
"children": {
"env_step": {
"total": 1897.6438436059896,
"count": 232883,
"self": 1602.8404388838296,
"children": {
"SubprocessEnvManager._take_step": {
"total": 291.861960438074,
"count": 232883,
"self": 16.813660515009815,
"children": {
"TorchPolicy.evaluate": {
"total": 275.0482999230642,
"count": 222962,
"self": 275.0482999230642
}
}
},
"workers": {
"total": 2.9414442840859465,
"count": 232883,
"self": 0.0,
"children": {
"worker_root": {
"total": 2437.6525703551283,
"count": 232883,
"is_parallel": true,
"self": 1125.663163677125,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011736879998807126,
"count": 1,
"is_parallel": true,
"self": 0.00032339999984287715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008502880000378354,
"count": 2,
"is_parallel": true,
"self": 0.0008502880000378354
}
}
},
"UnityEnvironment.step": {
"total": 0.02847588400004497,
"count": 1,
"is_parallel": true,
"self": 0.0003438210003423592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023182299992186017,
"count": 1,
"is_parallel": true,
"self": 0.00023182299992186017
},
"communicator.exchange": {
"total": 0.027163587999893934,
"count": 1,
"is_parallel": true,
"self": 0.027163587999893934
},
"steps_from_proto": {
"total": 0.0007366519998868171,
"count": 1,
"is_parallel": true,
"self": 0.00020156899995527056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005350829999315465,
"count": 2,
"is_parallel": true,
"self": 0.0005350829999315465
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1311.9894066780032,
"count": 232882,
"is_parallel": true,
"self": 40.40653430697171,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.05702253514028,
"count": 232882,
"is_parallel": true,
"self": 79.05702253514028
},
"communicator.exchange": {
"total": 1094.993356212909,
"count": 232882,
"is_parallel": true,
"self": 1094.993356212909
},
"steps_from_proto": {
"total": 97.5324936229822,
"count": 232882,
"is_parallel": true,
"self": 34.06822153891494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.46427208406726,
"count": 465764,
"is_parallel": true,
"self": 63.46427208406726
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.258932821095,
"count": 232883,
"self": 7.034301407092244,
"children": {
"process_trajectory": {
"total": 138.10628197500273,
"count": 232883,
"self": 136.78813365300243,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3181483220002974,
"count": 10,
"self": 1.3181483220002974
}
}
},
"_update_policy": {
"total": 388.118349439,
"count": 97,
"self": 327.67055782600073,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.447791612999254,
"count": 2910,
"self": 60.447791612999254
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.710001904750243e-07,
"count": 1,
"self": 9.710001904750243e-07
},
"TrainerController._save_models": {
"total": 0.11455132599985518,
"count": 1,
"self": 0.0026670610000110173,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11188426499984416,
"count": 1,
"self": 0.11188426499984416
}
}
}
}
}
}
}