ppo-Huggy / run_logs /timers.json
Vtmpas's picture
Huggy
e7a9e07
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4028527736663818,
"min": 1.4028527736663818,
"max": 1.4277318716049194,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70915.609375,
"min": 68686.4609375,
"max": 76710.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.29787234042553,
"min": 82.00332225913621,
"max": 389.2755905511811,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50900.0,
"min": 48372.0,
"max": 51180.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999920.0,
"min": 49695.0,
"max": 1999920.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999920.0,
"min": 49695.0,
"max": 1999920.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2203338146209717,
"min": 0.15261346101760864,
"max": 2.4080967903137207,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1101.2855224609375,
"min": 25.486448287963867,
"max": 1435.1986083984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5849368226755955,
"min": 1.954306310486226,
"max": 4.012465960177305,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1688.5052434802055,
"min": 246.24259512126446,
"max": 2327.3855204582214,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5849368226755955,
"min": 1.954306310486226,
"max": 4.012465960177305,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1688.5052434802055,
"min": 246.24259512126446,
"max": 2327.3855204582214,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017284785930193416,
"min": 0.014174336558789948,
"max": 0.0208420682970124,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05185435779058025,
"min": 0.028348673117579895,
"max": 0.05779164555472865,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04097345175428523,
"min": 0.020536313919971388,
"max": 0.049742782198720505,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12292035526285569,
"min": 0.041072627839942775,
"max": 0.14922834659616152,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7141987619666653e-06,
"min": 3.7141987619666653e-06,
"max": 0.00029532772655742497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1142596285899996e-05,
"min": 1.1142596285899996e-05,
"max": 0.0008442345185884997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123803333333335,
"min": 0.10123803333333335,
"max": 0.19844257499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30371410000000004,
"min": 0.20762580000000005,
"max": 0.5814115,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.177786333333333e-05,
"min": 7.177786333333333e-05,
"max": 0.004922284492500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021533358999999998,
"min": 0.00021533358999999998,
"max": 0.014072433850000001,
"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": "1688630004",
"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": "1688632370"
},
"total": 2366.175030142,
"count": 1,
"self": 0.44753818500021225,
"children": {
"run_training.setup": {
"total": 0.04829327699997066,
"count": 1,
"self": 0.04829327699997066
},
"TrainerController.start_learning": {
"total": 2365.67919868,
"count": 1,
"self": 4.132368968081664,
"children": {
"TrainerController._reset_env": {
"total": 4.732945163000068,
"count": 1,
"self": 4.732945163000068
},
"TrainerController.advance": {
"total": 2356.660636493918,
"count": 232067,
"self": 4.4091432967125,
"children": {
"env_step": {
"total": 1818.599063019122,
"count": 232067,
"self": 1520.7741035452386,
"children": {
"SubprocessEnvManager._take_step": {
"total": 295.1472028949174,
"count": 232067,
"self": 16.370377368888285,
"children": {
"TorchPolicy.evaluate": {
"total": 278.77682552602914,
"count": 222991,
"self": 278.77682552602914
}
}
},
"workers": {
"total": 2.677756578965841,
"count": 232067,
"self": 0.0,
"children": {
"worker_root": {
"total": 2357.9426266089617,
"count": 232067,
"is_parallel": true,
"self": 1119.9401068148609,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009024689999250768,
"count": 1,
"is_parallel": true,
"self": 0.0002631649999784713,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006393039999466055,
"count": 2,
"is_parallel": true,
"self": 0.0006393039999466055
}
}
},
"UnityEnvironment.step": {
"total": 0.053918718999966586,
"count": 1,
"is_parallel": true,
"self": 0.00036119699996106647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002490279999847189,
"count": 1,
"is_parallel": true,
"self": 0.0002490279999847189
},
"communicator.exchange": {
"total": 0.052577982999991946,
"count": 1,
"is_parallel": true,
"self": 0.052577982999991946
},
"steps_from_proto": {
"total": 0.000730511000028855,
"count": 1,
"is_parallel": true,
"self": 0.00020426600008249807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000526244999946357,
"count": 2,
"is_parallel": true,
"self": 0.000526244999946357
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1238.0025197941009,
"count": 232066,
"is_parallel": true,
"self": 39.22400096527804,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.93507112989619,
"count": 232066,
"is_parallel": true,
"self": 76.93507112989619
},
"communicator.exchange": {
"total": 1028.9146935859585,
"count": 232066,
"is_parallel": true,
"self": 1028.9146935859585
},
"steps_from_proto": {
"total": 92.92875411296814,
"count": 232066,
"is_parallel": true,
"self": 32.94435575404759,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.984398358920544,
"count": 464132,
"is_parallel": true,
"self": 59.984398358920544
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.6524301780837,
"count": 232067,
"self": 6.37264417799679,
"children": {
"process_trajectory": {
"total": 136.0453995510867,
"count": 232067,
"self": 134.29086213208598,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7545374190007124,
"count": 10,
"self": 1.7545374190007124
}
}
},
"_update_policy": {
"total": 391.2343864490002,
"count": 97,
"self": 323.9339528570014,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.30043359199885,
"count": 2910,
"self": 67.30043359199885
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0700000530050602e-06,
"count": 1,
"self": 1.0700000530050602e-06
},
"TrainerController._save_models": {
"total": 0.15324698499989609,
"count": 1,
"self": 0.002994218999901932,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15025276599999415,
"count": 1,
"self": 0.15025276599999415
}
}
}
}
}
}
}