ppo-Huggy / run_logs /timers.json
maliced's picture
Huggy
53be552 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4046123027801514,
"min": 1.4046123027801514,
"max": 1.4267208576202393,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69730.5703125,
"min": 69150.0546875,
"max": 77539.921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 69.97443181818181,
"min": 66.99183673469388,
"max": 405.41129032258067,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49262.0,
"min": 49213.0,
"max": 50271.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999945.0,
"min": 49646.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999945.0,
"min": 49646.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4820680618286133,
"min": 0.045057378709316254,
"max": 2.566758394241333,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1747.3759765625,
"min": 5.542057514190674,
"max": 1835.5296630859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.831299831159413,
"min": 1.835381714066839,
"max": 4.2264161331428065,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2697.2350811362267,
"min": 225.75195083022118,
"max": 2866.6587290763855,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.831299831159413,
"min": 1.835381714066839,
"max": 4.2264161331428065,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2697.2350811362267,
"min": 225.75195083022118,
"max": 2866.6587290763855,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019648535367741717,
"min": 0.01265455650985435,
"max": 0.020678019911671678,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05894560610322515,
"min": 0.0253091130197087,
"max": 0.06203405973501504,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06522158893446128,
"min": 0.020975790669520697,
"max": 0.06522158893446128,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19566476680338385,
"min": 0.041951581339041394,
"max": 0.19566476680338385,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.949398683566666e-06,
"min": 3.949398683566666e-06,
"max": 0.00029533080155640004,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1848196050699998e-05,
"min": 1.1848196050699998e-05,
"max": 0.0008442468185843998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131643333333333,
"min": 0.10131643333333333,
"max": 0.19844360000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039493,
"min": 0.20776050000000001,
"max": 0.5814155999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.569002333333333e-05,
"min": 7.569002333333333e-05,
"max": 0.004922335640000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022707007,
"min": 0.00022707007,
"max": 0.01407263844,
"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": "1765389547",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765392176"
},
"total": 2628.4466937119996,
"count": 1,
"self": 0.43403557200008436,
"children": {
"run_training.setup": {
"total": 0.02696066199996494,
"count": 1,
"self": 0.02696066199996494
},
"TrainerController.start_learning": {
"total": 2627.9856974779996,
"count": 1,
"self": 4.964214365022144,
"children": {
"TrainerController._reset_env": {
"total": 2.9926571070000136,
"count": 1,
"self": 2.9926571070000136
},
"TrainerController.advance": {
"total": 2619.9325598929777,
"count": 233559,
"self": 4.572144904823745,
"children": {
"env_step": {
"total": 2131.1442429410286,
"count": 233559,
"self": 1717.8920210359759,
"children": {
"SubprocessEnvManager._take_step": {
"total": 410.1152499020616,
"count": 233559,
"self": 16.11438424808489,
"children": {
"TorchPolicy.evaluate": {
"total": 394.0008656539767,
"count": 222925,
"self": 394.0008656539767
}
}
},
"workers": {
"total": 3.136972002991115,
"count": 233559,
"self": 0.0,
"children": {
"worker_root": {
"total": 2614.962277713053,
"count": 233559,
"is_parallel": true,
"self": 1226.7042249670765,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008064720000220404,
"count": 1,
"is_parallel": true,
"self": 0.00022527199985233892,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005812000001697015,
"count": 2,
"is_parallel": true,
"self": 0.0005812000001697015
}
}
},
"UnityEnvironment.step": {
"total": 0.028527412999892476,
"count": 1,
"is_parallel": true,
"self": 0.00035810800022773037,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020051899991813116,
"count": 1,
"is_parallel": true,
"self": 0.00020051899991813116
},
"communicator.exchange": {
"total": 0.027283773999897676,
"count": 1,
"is_parallel": true,
"self": 0.027283773999897676
},
"steps_from_proto": {
"total": 0.000685011999848939,
"count": 1,
"is_parallel": true,
"self": 0.0001855010000326729,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004995109998162661,
"count": 2,
"is_parallel": true,
"self": 0.0004995109998162661
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1388.2580527459766,
"count": 233558,
"is_parallel": true,
"self": 39.06940402995224,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.55688695396407,
"count": 233558,
"is_parallel": true,
"self": 81.55688695396407
},
"communicator.exchange": {
"total": 1175.187591248095,
"count": 233558,
"is_parallel": true,
"self": 1175.187591248095
},
"steps_from_proto": {
"total": 92.44417051396522,
"count": 233558,
"is_parallel": true,
"self": 31.45948820819899,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.98468230576623,
"count": 467116,
"is_parallel": true,
"self": 60.98468230576623
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 484.2161720471254,
"count": 233559,
"self": 7.267916591056064,
"children": {
"process_trajectory": {
"total": 163.83425718606713,
"count": 233559,
"self": 162.76759101206721,
"children": {
"RLTrainer._checkpoint": {
"total": 1.06666617399992,
"count": 10,
"self": 1.06666617399992
}
}
},
"_update_policy": {
"total": 313.1139982700022,
"count": 97,
"self": 248.23611569900436,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.87788257099783,
"count": 2910,
"self": 64.87788257099783
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.109999155043624e-07,
"count": 1,
"self": 9.109999155043624e-07
},
"TrainerController._save_models": {
"total": 0.09626520199981314,
"count": 1,
"self": 0.0012845819996982755,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09498062000011487,
"count": 1,
"self": 0.09498062000011487
}
}
}
}
}
}
}