ppo-Huggy / run_logs /timers.json
figurek1m's picture
Huggy
dff7c0a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407535195350647,
"min": 1.407535195350647,
"max": 1.4295055866241455,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68979.078125,
"min": 68529.8828125,
"max": 77686.703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.28378378378379,
"min": 78.31803797468355,
"max": 400.016,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49304.0,
"min": 49171.0,
"max": 50094.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999933.0,
"min": 49895.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999933.0,
"min": 49895.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4240620136260986,
"min": 0.09058869630098343,
"max": 2.458357572555542,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1435.044677734375,
"min": 11.23299789428711,
"max": 1523.554443359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.801506343725565,
"min": 1.890072452445184,
"max": 3.980136214427545,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2250.4917554855347,
"min": 234.36898410320282,
"max": 2440.75419986248,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.801506343725565,
"min": 1.890072452445184,
"max": 3.980136214427545,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2250.4917554855347,
"min": 234.36898410320282,
"max": 2440.75419986248,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01668400511844084,
"min": 0.013096454409242142,
"max": 0.019567737862234934,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05005201535532251,
"min": 0.026192908818484285,
"max": 0.056616264836581345,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054931667364305915,
"min": 0.023031559928009905,
"max": 0.05907248177876075,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16479500209291775,
"min": 0.04606311985601981,
"max": 0.1722839883218209,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.333848888750002e-06,
"min": 3.333848888750002e-06,
"max": 0.000295311676562775,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0001546666250006e-05,
"min": 1.0001546666250006e-05,
"max": 0.0008435884688038497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111125000000003,
"min": 0.10111125000000003,
"max": 0.19843722500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30333375000000007,
"min": 0.20739254999999995,
"max": 0.5811961499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.545137500000004e-05,
"min": 6.545137500000004e-05,
"max": 0.004922017527500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001963541250000001,
"min": 0.0001963541250000001,
"max": 0.014061687885,
"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": "1740492519",
"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": "1740495067"
},
"total": 2547.8773270399997,
"count": 1,
"self": 0.4376698619994386,
"children": {
"run_training.setup": {
"total": 0.023387661000015214,
"count": 1,
"self": 0.023387661000015214
},
"TrainerController.start_learning": {
"total": 2547.4162695170003,
"count": 1,
"self": 4.603568043005453,
"children": {
"TrainerController._reset_env": {
"total": 3.2754458350000277,
"count": 1,
"self": 3.2754458350000277
},
"TrainerController.advance": {
"total": 2539.4206110659948,
"count": 232664,
"self": 5.10000398494185,
"children": {
"env_step": {
"total": 2052.9323367300367,
"count": 232664,
"self": 1607.9289002490937,
"children": {
"SubprocessEnvManager._take_step": {
"total": 442.1590665589648,
"count": 232664,
"self": 16.29316309391561,
"children": {
"TorchPolicy.evaluate": {
"total": 425.8659034650492,
"count": 222887,
"self": 425.8659034650492
}
}
},
"workers": {
"total": 2.844369921978114,
"count": 232664,
"self": 0.0,
"children": {
"worker_root": {
"total": 2539.783135946011,
"count": 232664,
"is_parallel": true,
"self": 1230.9066746270123,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010644059999549427,
"count": 1,
"is_parallel": true,
"self": 0.000381495999931758,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006829100000231847,
"count": 2,
"is_parallel": true,
"self": 0.0006829100000231847
}
}
},
"UnityEnvironment.step": {
"total": 0.03485148899994783,
"count": 1,
"is_parallel": true,
"self": 0.0003663479999431729,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000245047000021259,
"count": 1,
"is_parallel": true,
"self": 0.000245047000021259
},
"communicator.exchange": {
"total": 0.03344870199998695,
"count": 1,
"is_parallel": true,
"self": 0.03344870199998695
},
"steps_from_proto": {
"total": 0.0007913919999964492,
"count": 1,
"is_parallel": true,
"self": 0.00022383099997114186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005675610000253073,
"count": 2,
"is_parallel": true,
"self": 0.0005675610000253073
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1308.8764613189987,
"count": 232663,
"is_parallel": true,
"self": 38.7576336830607,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.95319923296483,
"count": 232663,
"is_parallel": true,
"self": 85.95319923296483
},
"communicator.exchange": {
"total": 1094.096879087996,
"count": 232663,
"is_parallel": true,
"self": 1094.096879087996
},
"steps_from_proto": {
"total": 90.06874931497703,
"count": 232663,
"is_parallel": true,
"self": 33.79745404574078,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.27129526923625,
"count": 465326,
"is_parallel": true,
"self": 56.27129526923625
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.388270351016,
"count": 232664,
"self": 7.024012480094143,
"children": {
"process_trajectory": {
"total": 177.6664236689229,
"count": 232664,
"self": 176.34990969492344,
"children": {
"RLTrainer._checkpoint": {
"total": 1.316513973999463,
"count": 10,
"self": 1.316513973999463
}
}
},
"_update_policy": {
"total": 296.69783420199894,
"count": 97,
"self": 231.66859252000404,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.0292416819949,
"count": 2910,
"self": 65.0292416819949
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.830000635702163e-07,
"count": 1,
"self": 9.830000635702163e-07
},
"TrainerController._save_models": {
"total": 0.11664358999996693,
"count": 1,
"self": 0.0019152849999954924,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11472830499997144,
"count": 1,
"self": 0.11472830499997144
}
}
}
}
}
}
}