ppo-Huggy / run_logs /timers.json
layoric's picture
Huggy
ba9516f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066119194030762,
"min": 1.4065923690795898,
"max": 1.4274001121520996,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68988.6875,
"min": 68043.109375,
"max": 78439.0625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.79865771812081,
"min": 71.12987012987013,
"max": 441.87610619469024,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49348.0,
"min": 49164.0,
"max": 49974.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999945.0,
"min": 49295.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999945.0,
"min": 49295.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.485071897506714,
"min": 0.017260994762182236,
"max": 2.530749559402466,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1481.102783203125,
"min": 1.9332313537597656,
"max": 1712.568603515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7824511088980923,
"min": 1.8407298973096269,
"max": 4.0053157703880125,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2254.340860903263,
"min": 206.1617484986782,
"max": 2734.5885133743286,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7824511088980923,
"min": 1.8407298973096269,
"max": 4.0053157703880125,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2254.340860903263,
"min": 206.1617484986782,
"max": 2734.5885133743286,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017204967565743978,
"min": 0.014273443399482251,
"max": 0.02065141728283682,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05161490269723193,
"min": 0.028546886798964503,
"max": 0.058701087286074954,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06094646404186885,
"min": 0.02174206081156929,
"max": 0.06377204193009271,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18283939212560654,
"min": 0.04348412162313858,
"max": 0.19131612579027812,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.032248655950001e-06,
"min": 4.032248655950001e-06,
"max": 0.000295376926541025,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2096745967850002e-05,
"min": 1.2096745967850002e-05,
"max": 0.0008444749685083499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10134405,
"min": 0.10134405,
"max": 0.19845897499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30403215,
"min": 0.207821,
"max": 0.58149165,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.706809500000004e-05,
"min": 7.706809500000004e-05,
"max": 0.0049231028525,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00023120428500000013,
"min": 0.00023120428500000013,
"max": 0.014076433335000003,
"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": "1675826726",
"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=Huggy2 --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": "1675829236"
},
"total": 2510.0161985430004,
"count": 1,
"self": 0.4294578850003745,
"children": {
"run_training.setup": {
"total": 0.10822441100003743,
"count": 1,
"self": 0.10822441100003743
},
"TrainerController.start_learning": {
"total": 2509.478516247,
"count": 1,
"self": 4.519232699051372,
"children": {
"TrainerController._reset_env": {
"total": 10.813604712000028,
"count": 1,
"self": 10.813604712000028
},
"TrainerController.advance": {
"total": 2494.033362809948,
"count": 233284,
"self": 4.714000187927013,
"children": {
"env_step": {
"total": 1945.4342420900348,
"count": 233284,
"self": 1621.9263667450355,
"children": {
"SubprocessEnvManager._take_step": {
"total": 320.60031009902116,
"count": 233284,
"self": 16.62668309713331,
"children": {
"TorchPolicy.evaluate": {
"total": 303.97362700188785,
"count": 222942,
"self": 75.12582314184942,
"children": {
"TorchPolicy.sample_actions": {
"total": 228.84780386003843,
"count": 222942,
"self": 228.84780386003843
}
}
}
}
},
"workers": {
"total": 2.9075652459781622,
"count": 233284,
"self": 0.0,
"children": {
"worker_root": {
"total": 2501.049549890978,
"count": 233284,
"is_parallel": true,
"self": 1181.431690471938,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020522340000752592,
"count": 1,
"is_parallel": true,
"self": 0.00036262900005112897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016896050000241303,
"count": 2,
"is_parallel": true,
"self": 0.0016896050000241303
}
}
},
"UnityEnvironment.step": {
"total": 0.07446345999994719,
"count": 1,
"is_parallel": true,
"self": 0.0003010869999116039,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022354700001869787,
"count": 1,
"is_parallel": true,
"self": 0.00022354700001869787
},
"communicator.exchange": {
"total": 0.0731630860000223,
"count": 1,
"is_parallel": true,
"self": 0.0731630860000223
},
"steps_from_proto": {
"total": 0.0007757399999945847,
"count": 1,
"is_parallel": true,
"self": 0.0002459969999790701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005297430000155146,
"count": 2,
"is_parallel": true,
"self": 0.0005297430000155146
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1319.61785941904,
"count": 233283,
"is_parallel": true,
"self": 38.435792372039714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.98286965409625,
"count": 233283,
"is_parallel": true,
"self": 83.98286965409625
},
"communicator.exchange": {
"total": 1095.7954892119874,
"count": 233283,
"is_parallel": true,
"self": 1095.7954892119874
},
"steps_from_proto": {
"total": 101.40370818091674,
"count": 233283,
"is_parallel": true,
"self": 41.736953205037025,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.66675497587971,
"count": 466566,
"is_parallel": true,
"self": 59.66675497587971
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 543.8851205319863,
"count": 233284,
"self": 6.5358373550079705,
"children": {
"process_trajectory": {
"total": 177.5610292969783,
"count": 233284,
"self": 176.2569353739783,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3040939229999822,
"count": 10,
"self": 1.3040939229999822
}
}
},
"_update_policy": {
"total": 359.78825388000007,
"count": 97,
"self": 302.08595136299766,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.70230251700241,
"count": 2910,
"self": 57.70230251700241
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1800002539530396e-06,
"count": 1,
"self": 1.1800002539530396e-06
},
"TrainerController._save_models": {
"total": 0.11231484600011754,
"count": 1,
"self": 0.0025771989999157086,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10973764700020183,
"count": 1,
"self": 0.10973764700020183
}
}
}
}
}
}
}