ppo-Huggy / run_logs /timers.json
udonhef2bmad's picture
Huggy
2b3f638 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407983660697937,
"min": 1.407983660697937,
"max": 1.4270038604736328,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70349.90625,
"min": 68674.515625,
"max": 77187.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 71.0966810966811,
"min": 70.87769784172662,
"max": 423.83898305084745,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49270.0,
"min": 48691.0,
"max": 50013.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49889.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49889.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4685332775115967,
"min": 0.16492784023284912,
"max": 2.519385576248169,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1710.6934814453125,
"min": 19.29655647277832,
"max": 1710.6934814453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8684631101840847,
"min": 1.8623370879735701,
"max": 4.058081167752926,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2680.8449353575706,
"min": 217.89343929290771,
"max": 2710.1340205073357,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8684631101840847,
"min": 1.8623370879735701,
"max": 4.058081167752926,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2680.8449353575706,
"min": 217.89343929290771,
"max": 2710.1340205073357,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017133291942829806,
"min": 0.013907397326208108,
"max": 0.020595525571520234,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051399875828489414,
"min": 0.027814794652416215,
"max": 0.0617865767145607,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056564700520700874,
"min": 0.02109465120981137,
"max": 0.06113571791599194,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16969410156210263,
"min": 0.04218930241962274,
"max": 0.18226573914289473,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.843948718716659e-06,
"min": 3.843948718716659e-06,
"max": 0.000295289776570075,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1531846156149978e-05,
"min": 1.1531846156149978e-05,
"max": 0.0008439783186738998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128128333333332,
"min": 0.10128128333333332,
"max": 0.19842992499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30384384999999997,
"min": 0.2076884,
"max": 0.5813260999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.393603833333324e-05,
"min": 7.393603833333324e-05,
"max": 0.0049216532574999985,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022180811499999972,
"min": 0.00022180811499999972,
"max": 0.014068172390000005,
"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": "1739394416",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739396845"
},
"total": 2428.323248492,
"count": 1,
"self": 0.4409104169994862,
"children": {
"run_training.setup": {
"total": 0.023198233000016444,
"count": 1,
"self": 0.023198233000016444
},
"TrainerController.start_learning": {
"total": 2427.8591398420003,
"count": 1,
"self": 4.628309083077056,
"children": {
"TrainerController._reset_env": {
"total": 3.4631827630000203,
"count": 1,
"self": 3.4631827630000203
},
"TrainerController.advance": {
"total": 2419.656924529923,
"count": 233080,
"self": 4.53374860404665,
"children": {
"env_step": {
"total": 1896.514704446914,
"count": 233080,
"self": 1485.6451798320168,
"children": {
"SubprocessEnvManager._take_step": {
"total": 408.3024945939607,
"count": 233080,
"self": 15.495131020092686,
"children": {
"TorchPolicy.evaluate": {
"total": 392.80736357386803,
"count": 222870,
"self": 392.80736357386803
}
}
},
"workers": {
"total": 2.5670300209366133,
"count": 233080,
"self": 0.0,
"children": {
"worker_root": {
"total": 2420.5595397909638,
"count": 233080,
"is_parallel": true,
"self": 1208.6405937419286,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001020086000039555,
"count": 1,
"is_parallel": true,
"self": 0.0002572530000293227,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007628330000102324,
"count": 2,
"is_parallel": true,
"self": 0.0007628330000102324
}
}
},
"UnityEnvironment.step": {
"total": 0.028814441000008628,
"count": 1,
"is_parallel": true,
"self": 0.0003435080000144808,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023665200001232733,
"count": 1,
"is_parallel": true,
"self": 0.00023665200001232733
},
"communicator.exchange": {
"total": 0.02752423900000167,
"count": 1,
"is_parallel": true,
"self": 0.02752423900000167
},
"steps_from_proto": {
"total": 0.0007100419999801488,
"count": 1,
"is_parallel": true,
"self": 0.00019499899991615166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005150430000639972,
"count": 2,
"is_parallel": true,
"self": 0.0005150430000639972
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1211.9189460490352,
"count": 233079,
"is_parallel": true,
"self": 37.128545586926975,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.22227085700382,
"count": 233079,
"is_parallel": true,
"self": 79.22227085700382
},
"communicator.exchange": {
"total": 1010.619667604069,
"count": 233079,
"is_parallel": true,
"self": 1010.619667604069
},
"steps_from_proto": {
"total": 84.9484620010353,
"count": 233079,
"is_parallel": true,
"self": 29.985814070054744,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.96264793098055,
"count": 466158,
"is_parallel": true,
"self": 54.96264793098055
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.6084714789623,
"count": 233080,
"self": 6.211680087913351,
"children": {
"process_trajectory": {
"total": 166.23324860605152,
"count": 233080,
"self": 164.94889288705082,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2843557190007004,
"count": 10,
"self": 1.2843557190007004
}
}
},
"_update_policy": {
"total": 346.1635427849975,
"count": 97,
"self": 278.0732622789904,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.0902805060071,
"count": 2910,
"self": 68.0902805060071
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.410000529896934e-07,
"count": 1,
"self": 9.410000529896934e-07
},
"TrainerController._save_models": {
"total": 0.1107225250002557,
"count": 1,
"self": 0.0018841980004253855,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10883832699983031,
"count": 1,
"self": 0.10883832699983031
}
}
}
}
}
}
}