{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4075660705566406,
"min": 1.4075660705566406,
"max": 1.4293336868286133,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69321.21875,
"min": 68312.25,
"max": 76080.4140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 106.96544276457884,
"min": 104.27426160337552,
"max": 405.6910569105691,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49525.0,
"min": 48951.0,
"max": 50243.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49774.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49774.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3100593090057373,
"min": 0.0704134926199913,
"max": 2.354785919189453,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1069.5574951171875,
"min": 8.590446472167969,
"max": 1093.516845703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.62864886838983,
"min": 1.9503000793886967,
"max": 3.659143411300399,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1680.0644260644913,
"min": 237.936609685421,
"max": 1698.3010804057121,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.62864886838983,
"min": 1.9503000793886967,
"max": 3.659143411300399,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1680.0644260644913,
"min": 237.936609685421,
"max": 1698.3010804057121,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01677426046032148,
"min": 0.013943707008244625,
"max": 0.021377448205991335,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03354852092064296,
"min": 0.02788741401648925,
"max": 0.05665091521126063,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04835579072435697,
"min": 0.022203938538829487,
"max": 0.05614446024927828,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09671158144871395,
"min": 0.044407877077658975,
"max": 0.16843338074783484,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.94217368597499e-06,
"min": 3.94217368597499e-06,
"max": 0.0002953602015466001,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.88434737194998e-06,
"min": 7.88434737194998e-06,
"max": 0.0008442639185786999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131402499999999,
"min": 0.10131402499999999,
"max": 0.1984534,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20262804999999998,
"min": 0.20262804999999998,
"max": 0.5814212999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.55698474999998e-05,
"min": 7.55698474999998e-05,
"max": 0.00492282466,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001511396949999996,
"min": 0.0001511396949999996,
"max": 0.014072922869999999,
"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": "1692753819",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692756409"
},
"total": 2589.540690286,
"count": 1,
"self": 0.4902193419998184,
"children": {
"run_training.setup": {
"total": 0.043547620000026654,
"count": 1,
"self": 0.043547620000026654
},
"TrainerController.start_learning": {
"total": 2589.006923324,
"count": 1,
"self": 4.846563719141159,
"children": {
"TrainerController._reset_env": {
"total": 4.30752451699999,
"count": 1,
"self": 4.30752451699999
},
"TrainerController.advance": {
"total": 2579.723552740859,
"count": 230235,
"self": 5.259380008871176,
"children": {
"env_step": {
"total": 1998.2664047241108,
"count": 230235,
"self": 1687.3728217310797,
"children": {
"SubprocessEnvManager._take_step": {
"total": 307.78703181103924,
"count": 230235,
"self": 17.80349465097845,
"children": {
"TorchPolicy.evaluate": {
"total": 289.9835371600608,
"count": 222802,
"self": 289.9835371600608
}
}
},
"workers": {
"total": 3.106551181991847,
"count": 230235,
"self": 0.0,
"children": {
"worker_root": {
"total": 2580.882450069147,
"count": 230235,
"is_parallel": true,
"self": 1206.1625066411036,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009556869999869377,
"count": 1,
"is_parallel": true,
"self": 0.0002983159999985219,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006573709999884159,
"count": 2,
"is_parallel": true,
"self": 0.0006573709999884159
}
}
},
"UnityEnvironment.step": {
"total": 0.028550101000007544,
"count": 1,
"is_parallel": true,
"self": 0.00035991599997942103,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002275620000204981,
"count": 1,
"is_parallel": true,
"self": 0.0002275620000204981
},
"communicator.exchange": {
"total": 0.02723165700001573,
"count": 1,
"is_parallel": true,
"self": 0.02723165700001573
},
"steps_from_proto": {
"total": 0.0007309659999918949,
"count": 1,
"is_parallel": true,
"self": 0.00019747200002484533,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005334939999670496,
"count": 2,
"is_parallel": true,
"self": 0.0005334939999670496
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1374.7199434280435,
"count": 230234,
"is_parallel": true,
"self": 42.20831402499266,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.16023797505892,
"count": 230234,
"is_parallel": true,
"self": 86.16023797505892
},
"communicator.exchange": {
"total": 1143.0921464429196,
"count": 230234,
"is_parallel": true,
"self": 1143.0921464429196
},
"steps_from_proto": {
"total": 103.25924498507237,
"count": 230234,
"is_parallel": true,
"self": 35.73554114699135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.52370383808102,
"count": 460468,
"is_parallel": true,
"self": 67.52370383808102
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 576.1977680078769,
"count": 230235,
"self": 7.452969028903794,
"children": {
"process_trajectory": {
"total": 136.96136128497255,
"count": 230235,
"self": 135.58578068097233,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3755806040002199,
"count": 10,
"self": 1.3755806040002199
}
}
},
"_update_policy": {
"total": 431.78343769400055,
"count": 96,
"self": 368.64476604399846,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.138671650002095,
"count": 2880,
"self": 63.138671650002095
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2830000741814729e-06,
"count": 1,
"self": 1.2830000741814729e-06
},
"TrainerController._save_models": {
"total": 0.12928106400022443,
"count": 1,
"self": 0.0021375060000536905,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12714355800017074,
"count": 1,
"self": 0.12714355800017074
}
}
}
}
}
}
}