ppo-Huggy / run_logs /timers.json
letaldir's picture
Huggy
ad09531 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4056062698364258,
"min": 1.4056062698364258,
"max": 1.4273712635040283,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70474.2890625,
"min": 69049.6953125,
"max": 76242.3984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.31740614334471,
"min": 81.96019900497512,
"max": 390.8828125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49410.0,
"min": 49014.0,
"max": 50033.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999987.0,
"min": 49982.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999987.0,
"min": 49982.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4341375827789307,
"min": 0.030215848237276077,
"max": 2.4921457767486572,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1426.4046630859375,
"min": 3.8374128341674805,
"max": 1463.060546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7646076263217796,
"min": 1.8310211124851947,
"max": 3.942440052330494,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2206.060069024563,
"min": 232.53968128561974,
"max": 2314.4114862680435,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7646076263217796,
"min": 1.8310211124851947,
"max": 3.942440052330494,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2206.060069024563,
"min": 232.53968128561974,
"max": 2314.4114862680435,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018751955478607366,
"min": 0.011937684516306037,
"max": 0.019912419176156014,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0562558664358221,
"min": 0.023875369032612073,
"max": 0.056499175774903654,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06184754367503856,
"min": 0.021891854579250018,
"max": 0.06184754367503856,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18554263102511567,
"min": 0.043783709158500037,
"max": 0.18554263102511567,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.541598819499997e-06,
"min": 3.541598819499997e-06,
"max": 0.00029535105154964987,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.062479645849999e-05,
"min": 1.062479645849999e-05,
"max": 0.0008442924185691999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011805,
"min": 0.1011805,
"max": 0.19845035000000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035415,
"min": 0.2074968,
"max": 0.5814307999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.890694999999995e-05,
"min": 6.890694999999995e-05,
"max": 0.004922672465,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020672084999999986,
"min": 0.00020672084999999986,
"max": 0.014073396920000002,
"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": "1759292782",
"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": "1759295265"
},
"total": 2482.494755495,
"count": 1,
"self": 0.4444689499996457,
"children": {
"run_training.setup": {
"total": 0.024722600000018247,
"count": 1,
"self": 0.024722600000018247
},
"TrainerController.start_learning": {
"total": 2482.025563945,
"count": 1,
"self": 4.022167059936237,
"children": {
"TrainerController._reset_env": {
"total": 3.0016310050000357,
"count": 1,
"self": 3.0016310050000357
},
"TrainerController.advance": {
"total": 2474.907781074064,
"count": 232517,
"self": 4.1729632550445785,
"children": {
"env_step": {
"total": 2023.683457124997,
"count": 232517,
"self": 1635.6820698521249,
"children": {
"SubprocessEnvManager._take_step": {
"total": 385.3857279689157,
"count": 232517,
"self": 14.624206545033132,
"children": {
"TorchPolicy.evaluate": {
"total": 370.7615214238826,
"count": 222972,
"self": 370.7615214238826
}
}
},
"workers": {
"total": 2.61565930395642,
"count": 232517,
"self": 0.0,
"children": {
"worker_root": {
"total": 2469.389789976959,
"count": 232517,
"is_parallel": true,
"self": 1140.4026391469697,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000814331000015045,
"count": 1,
"is_parallel": true,
"self": 0.00022093900003028466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005933919999847603,
"count": 2,
"is_parallel": true,
"self": 0.0005933919999847603
}
}
},
"UnityEnvironment.step": {
"total": 0.03346316500000057,
"count": 1,
"is_parallel": true,
"self": 0.0003340549999961695,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022125899999991816,
"count": 1,
"is_parallel": true,
"self": 0.00022125899999991816
},
"communicator.exchange": {
"total": 0.03061713699997881,
"count": 1,
"is_parallel": true,
"self": 0.03061713699997881
},
"steps_from_proto": {
"total": 0.002290714000025673,
"count": 1,
"is_parallel": true,
"self": 0.001396728000031544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008939859999941291,
"count": 2,
"is_parallel": true,
"self": 0.0008939859999941291
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1328.9871508299893,
"count": 232516,
"is_parallel": true,
"self": 36.75299639323157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.04243744886196,
"count": 232516,
"is_parallel": true,
"self": 79.04243744886196
},
"communicator.exchange": {
"total": 1126.4272789529387,
"count": 232516,
"is_parallel": true,
"self": 1126.4272789529387
},
"steps_from_proto": {
"total": 86.76443803495698,
"count": 232516,
"is_parallel": true,
"self": 30.434178089927798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.330259945029184,
"count": 465032,
"is_parallel": true,
"self": 56.330259945029184
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 447.0513606940224,
"count": 232517,
"self": 6.378010946919744,
"children": {
"process_trajectory": {
"total": 152.10840271910263,
"count": 232517,
"self": 150.9525227481014,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1558799710012408,
"count": 10,
"self": 1.1558799710012408
}
}
},
"_update_policy": {
"total": 288.564947028,
"count": 97,
"self": 228.04140701100653,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.52354001699348,
"count": 2910,
"self": 60.52354001699348
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.619999789516442e-07,
"count": 1,
"self": 8.619999789516442e-07
},
"TrainerController._save_models": {
"total": 0.09398394399977406,
"count": 1,
"self": 0.001509456999883696,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09247448699989036,
"count": 1,
"self": 0.09247448699989036
}
}
}
}
}
}
}