ppo-Huggy / run_logs /timers.json
opria123's picture
Huggy
d52ab4e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4028435945510864,
"min": 1.4028435945510864,
"max": 1.428662896156311,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70850.6171875,
"min": 66910.9140625,
"max": 78432.8359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 129.57742782152232,
"min": 123.9175,
"max": 410.05737704918033,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49369.0,
"min": 49065.0,
"max": 50212.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999592.0,
"min": 49874.0,
"max": 1999592.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999592.0,
"min": 49874.0,
"max": 1999592.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2067501544952393,
"min": -0.04146943986415863,
"max": 2.284285545349121,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 840.7717895507812,
"min": -5.0178022384643555,
"max": 909.1456298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3607881209981723,
"min": 1.7067064690934726,
"max": 3.505660955630355,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1280.4602741003036,
"min": 206.51148276031017,
"max": 1395.2530603408813,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3607881209981723,
"min": 1.7067064690934726,
"max": 3.505660955630355,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1280.4602741003036,
"min": 206.51148276031017,
"max": 1395.2530603408813,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016492970460967628,
"min": 0.014442099875304848,
"max": 0.0208487301308196,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.032985940921935256,
"min": 0.028884199750609695,
"max": 0.05673072658003851,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05003674228986105,
"min": 0.02351599478473266,
"max": 0.060896631206075344,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1000734845797221,
"min": 0.04703198956946532,
"max": 0.17529606347282728,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3532738822749923e-06,
"min": 3.3532738822749923e-06,
"max": 0.00029535667654777503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 6.7065477645499845e-06,
"min": 6.7065477645499845e-06,
"max": 0.0008442939185686999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111772500000005,
"min": 0.10111772500000005,
"max": 0.198452225,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2022354500000001,
"min": 0.2022354500000001,
"max": 0.5814313000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.577447749999988e-05,
"min": 6.577447749999988e-05,
"max": 0.004922766027499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00013154895499999976,
"min": 0.00013154895499999976,
"max": 0.01407342187,
"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": "1744754174",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ../content/ml-agents/config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1744756577"
},
"total": 2402.973101756,
"count": 1,
"self": 0.43921937799950683,
"children": {
"run_training.setup": {
"total": 0.032083328000226174,
"count": 1,
"self": 0.032083328000226174
},
"TrainerController.start_learning": {
"total": 2402.50179905,
"count": 1,
"self": 4.253924851997908,
"children": {
"TrainerController._reset_env": {
"total": 3.8233303970000634,
"count": 1,
"self": 3.8233303970000634
},
"TrainerController.advance": {
"total": 2394.3046933130026,
"count": 229288,
"self": 4.285943106240666,
"children": {
"env_step": {
"total": 1922.0649309609926,
"count": 229288,
"self": 1499.8151063651385,
"children": {
"SubprocessEnvManager._take_step": {
"total": 419.6832149548991,
"count": 229288,
"self": 15.537298820150681,
"children": {
"TorchPolicy.evaluate": {
"total": 404.1459161347484,
"count": 222888,
"self": 404.1459161347484
}
}
},
"workers": {
"total": 2.5666096409549937,
"count": 229288,
"self": 0.0,
"children": {
"worker_root": {
"total": 2395.255350960123,
"count": 229288,
"is_parallel": true,
"self": 1168.7574468480016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001162266999926942,
"count": 1,
"is_parallel": true,
"self": 0.0003932110003006528,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007690559996262891,
"count": 2,
"is_parallel": true,
"self": 0.0007690559996262891
}
}
},
"UnityEnvironment.step": {
"total": 0.030439920000389975,
"count": 1,
"is_parallel": true,
"self": 0.0002994380001837271,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018730299962044228,
"count": 1,
"is_parallel": true,
"self": 0.00018730299962044228
},
"communicator.exchange": {
"total": 0.029089376999763772,
"count": 1,
"is_parallel": true,
"self": 0.029089376999763772
},
"steps_from_proto": {
"total": 0.0008638020008220337,
"count": 1,
"is_parallel": true,
"self": 0.00018592700052977307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006778750002922607,
"count": 2,
"is_parallel": true,
"self": 0.0006778750002922607
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1226.4979041121214,
"count": 229287,
"is_parallel": true,
"self": 36.009744765397045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.4092699957746,
"count": 229287,
"is_parallel": true,
"self": 79.4092699957746
},
"communicator.exchange": {
"total": 1026.9650183380327,
"count": 229287,
"is_parallel": true,
"self": 1026.9650183380327
},
"steps_from_proto": {
"total": 84.11387101291712,
"count": 229287,
"is_parallel": true,
"self": 29.322231733635817,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.7916392792813,
"count": 458574,
"is_parallel": true,
"self": 54.7916392792813
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 467.9538192457694,
"count": 229288,
"self": 6.483439804789668,
"children": {
"process_trajectory": {
"total": 142.32409642398216,
"count": 229288,
"self": 140.81802705098016,
"children": {
"RLTrainer._checkpoint": {
"total": 1.506069373001992,
"count": 10,
"self": 1.506069373001992
}
}
},
"_update_policy": {
"total": 319.1462830169976,
"count": 96,
"self": 252.8527216829816,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.29356133401598,
"count": 2880,
"self": 66.29356133401598
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.97999746282585e-07,
"count": 1,
"self": 7.97999746282585e-07
},
"TrainerController._save_models": {
"total": 0.1198496899996826,
"count": 1,
"self": 0.0020421099998202408,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11780757999986236,
"count": 1,
"self": 0.11780757999986236
}
}
}
}
}
}
}