ppo-Huggy / run_logs /timers.json
mlewand's picture
Huggy
17c0def
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3992103338241577,
"min": 1.3992103338241577,
"max": 1.4267228841781616,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70181.59375,
"min": 68174.8984375,
"max": 78659.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.33167495854063,
"min": 79.60096930533118,
"max": 411.0406504065041,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49646.0,
"min": 48729.0,
"max": 50558.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999529.0,
"min": 49931.0,
"max": 1999529.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999529.0,
"min": 49931.0,
"max": 1999529.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4527461528778076,
"min": 0.1609315574169159,
"max": 2.4837160110473633,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1479.005859375,
"min": 19.633649826049805,
"max": 1479.005859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8457422150703606,
"min": 1.866492737389979,
"max": 4.0101515320838725,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2318.9825556874275,
"min": 227.71211396157742,
"max": 2318.9825556874275,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8457422150703606,
"min": 1.866492737389979,
"max": 4.0101515320838725,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2318.9825556874275,
"min": 227.71211396157742,
"max": 2318.9825556874275,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016250140774011216,
"min": 0.012499070921668931,
"max": 0.020962030542674863,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04875042232203365,
"min": 0.024998141843337863,
"max": 0.055076137355839216,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05449453343947729,
"min": 0.020765541835377613,
"max": 0.06690130333105723,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16348360031843187,
"min": 0.041531083670755226,
"max": 0.193545438721776,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2703989098999935e-06,
"min": 3.2703989098999935e-06,
"max": 0.0002952820515726499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.811196729699981e-06,
"min": 9.811196729699981e-06,
"max": 0.0008438631187123,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010901,
"min": 0.1010901,
"max": 0.19842734999999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032703,
"min": 0.2073098,
"max": 0.5812877000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.43959899999999e-05,
"min": 6.43959899999999e-05,
"max": 0.004921524765000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001931879699999997,
"min": 0.0001931879699999997,
"max": 0.01406625623,
"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": "1676484479",
"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": "1676486835"
},
"total": 2356.115825358,
"count": 1,
"self": 0.43582582499993805,
"children": {
"run_training.setup": {
"total": 0.10776874999999109,
"count": 1,
"self": 0.10776874999999109
},
"TrainerController.start_learning": {
"total": 2355.572230783,
"count": 1,
"self": 3.9772173230389853,
"children": {
"TrainerController._reset_env": {
"total": 11.199321513999962,
"count": 1,
"self": 11.199321513999962
},
"TrainerController.advance": {
"total": 2340.285807819961,
"count": 232136,
"self": 4.401898318851636,
"children": {
"env_step": {
"total": 1826.943198042981,
"count": 232136,
"self": 1535.6961528209818,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.54717110204024,
"count": 232136,
"self": 15.082376470999861,
"children": {
"TorchPolicy.evaluate": {
"total": 273.4647946310404,
"count": 222894,
"self": 68.96903381497668,
"children": {
"TorchPolicy.sample_actions": {
"total": 204.4957608160637,
"count": 222894,
"self": 204.4957608160637
}
}
}
}
},
"workers": {
"total": 2.699874119959077,
"count": 232136,
"self": 0.0,
"children": {
"worker_root": {
"total": 2347.6129923720114,
"count": 232136,
"is_parallel": true,
"self": 1091.7746919149868,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001963715000101729,
"count": 1,
"is_parallel": true,
"self": 0.00035501400009252393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001608701000009205,
"count": 2,
"is_parallel": true,
"self": 0.001608701000009205
}
}
},
"UnityEnvironment.step": {
"total": 0.02869164800006274,
"count": 1,
"is_parallel": true,
"self": 0.0002822370001922536,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022438399992097402,
"count": 1,
"is_parallel": true,
"self": 0.00022438399992097402
},
"communicator.exchange": {
"total": 0.02749843099991267,
"count": 1,
"is_parallel": true,
"self": 0.02749843099991267
},
"steps_from_proto": {
"total": 0.0006865960000368432,
"count": 1,
"is_parallel": true,
"self": 0.00023539699986940832,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045119900016743486,
"count": 2,
"is_parallel": true,
"self": 0.00045119900016743486
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1255.8383004570246,
"count": 232135,
"is_parallel": true,
"self": 38.04419166113712,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.18713560793606,
"count": 232135,
"is_parallel": true,
"self": 78.18713560793606
},
"communicator.exchange": {
"total": 1035.1372653479032,
"count": 232135,
"is_parallel": true,
"self": 1035.1372653479032
},
"steps_from_proto": {
"total": 104.46970784004816,
"count": 232135,
"is_parallel": true,
"self": 37.351775070156464,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.1179327698917,
"count": 464270,
"is_parallel": true,
"self": 67.1179327698917
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 508.94071145812836,
"count": 232136,
"self": 6.225274871173497,
"children": {
"process_trajectory": {
"total": 159.41891430595467,
"count": 232136,
"self": 158.11337925795385,
"children": {
"RLTrainer._checkpoint": {
"total": 1.30553504800082,
"count": 10,
"self": 1.30553504800082
}
}
},
"_update_policy": {
"total": 343.2965222810002,
"count": 97,
"self": 287.13072325900964,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.16579902199055,
"count": 2910,
"self": 56.16579902199055
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2000000424450263e-06,
"count": 1,
"self": 1.2000000424450263e-06
},
"TrainerController._save_models": {
"total": 0.10988292599995475,
"count": 1,
"self": 0.0030609049999839044,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10682202099997085,
"count": 1,
"self": 0.10682202099997085
}
}
}
}
}
}
}