ppo-Huggy / run_logs /timers.json
malerbe's picture
Huggy
ab60910 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066369533538818,
"min": 1.4066369533538818,
"max": 1.4287898540496826,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70572.3828125,
"min": 68388.078125,
"max": 78520.359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.06902654867257,
"min": 81.09983361064891,
"max": 405.3225806451613,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49194.0,
"min": 48741.0,
"max": 50260.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49634.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49634.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4895827770233154,
"min": 0.1315750777721405,
"max": 2.4895827770233154,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1406.6142578125,
"min": 16.183734893798828,
"max": 1456.327880859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.839953735549893,
"min": 1.6271613779349057,
"max": 3.9479120916395045,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2169.5738605856895,
"min": 200.14084948599339,
"max": 2311.770408153534,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.839953735549893,
"min": 1.6271613779349057,
"max": 3.9479120916395045,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2169.5738605856895,
"min": 200.14084948599339,
"max": 2311.770408153534,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01737199833700692,
"min": 0.014577163821801756,
"max": 0.020876196773315314,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05211599501102076,
"min": 0.02915432764360351,
"max": 0.058963688522150434,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0594560846272442,
"min": 0.022424495841066042,
"max": 0.06671631907423338,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1783682538817326,
"min": 0.044848991682132085,
"max": 0.18568030682702857,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.758448747216665e-06,
"min": 3.758448747216665e-06,
"max": 0.0002953173015609,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1275346241649995e-05,
"min": 1.1275346241649995e-05,
"max": 0.0008441541186153,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125278333333336,
"min": 0.10125278333333336,
"max": 0.19843910000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30375835000000007,
"min": 0.20767549999999993,
"max": 0.5813847,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.251388833333333e-05,
"min": 7.251388833333333e-05,
"max": 0.00492211109,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021754166499999997,
"min": 0.00021754166499999997,
"max": 0.01407109653,
"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": "1716535318",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716538014"
},
"total": 2695.084795305,
"count": 1,
"self": 0.43833199200025774,
"children": {
"run_training.setup": {
"total": 0.0570520250000186,
"count": 1,
"self": 0.0570520250000186
},
"TrainerController.start_learning": {
"total": 2694.589411288,
"count": 1,
"self": 5.224491810011841,
"children": {
"TrainerController._reset_env": {
"total": 2.9796616250000056,
"count": 1,
"self": 2.9796616250000056
},
"TrainerController.advance": {
"total": 2686.2698128959883,
"count": 232323,
"self": 5.21363721009584,
"children": {
"env_step": {
"total": 2153.1393118589663,
"count": 232323,
"self": 1773.4816111068706,
"children": {
"SubprocessEnvManager._take_step": {
"total": 376.217246310031,
"count": 232323,
"self": 20.43211289110127,
"children": {
"TorchPolicy.evaluate": {
"total": 355.7851334189297,
"count": 222996,
"self": 355.7851334189297
}
}
},
"workers": {
"total": 3.44045444206472,
"count": 232323,
"self": 0.0,
"children": {
"worker_root": {
"total": 2686.4218564420016,
"count": 232323,
"is_parallel": true,
"self": 1261.8043773538611,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008989149999933943,
"count": 1,
"is_parallel": true,
"self": 0.0002532469999891873,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000645668000004207,
"count": 2,
"is_parallel": true,
"self": 0.000645668000004207
}
}
},
"UnityEnvironment.step": {
"total": 0.044842777999974714,
"count": 1,
"is_parallel": true,
"self": 0.00041056999998545507,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019062000001213164,
"count": 1,
"is_parallel": true,
"self": 0.00019062000001213164
},
"communicator.exchange": {
"total": 0.04350092999999333,
"count": 1,
"is_parallel": true,
"self": 0.04350092999999333
},
"steps_from_proto": {
"total": 0.0007406579999837959,
"count": 1,
"is_parallel": true,
"self": 0.00021447799991847205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005261800000653238,
"count": 2,
"is_parallel": true,
"self": 0.0005261800000653238
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1424.6174790881405,
"count": 232322,
"is_parallel": true,
"self": 42.535178556157916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.70263897105843,
"count": 232322,
"is_parallel": true,
"self": 90.70263897105843
},
"communicator.exchange": {
"total": 1191.100224389007,
"count": 232322,
"is_parallel": true,
"self": 1191.100224389007
},
"steps_from_proto": {
"total": 100.27943717191727,
"count": 232322,
"is_parallel": true,
"self": 37.521640590705545,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.75779658121172,
"count": 464644,
"is_parallel": true,
"self": 62.75779658121172
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.9168638269259,
"count": 232323,
"self": 8.269484117921365,
"children": {
"process_trajectory": {
"total": 174.12497484400507,
"count": 232323,
"self": 172.68862518200518,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4363496619998841,
"count": 10,
"self": 1.4363496619998841
}
}
},
"_update_policy": {
"total": 345.52240486499954,
"count": 97,
"self": 279.82589416901465,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.6965106959849,
"count": 2910,
"self": 65.6965106959849
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.43000031838892e-07,
"count": 1,
"self": 9.43000031838892e-07
},
"TrainerController._save_models": {
"total": 0.11544401399987692,
"count": 1,
"self": 0.0018336940001972835,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11361031999967963,
"count": 1,
"self": 0.11361031999967963
}
}
}
}
}
}
}