ppo-Huggy / run_logs /timers.json
Ferchi00's picture
Huggy
077dc89 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4083352088928223,
"min": 1.4083352088928223,
"max": 1.4302819967269897,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69960.4609375,
"min": 69207.46875,
"max": 76278.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.24333333333334,
"min": 77.27742946708464,
"max": 412.74380165289256,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49346.0,
"min": 49103.0,
"max": 50158.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999954.0,
"min": 49892.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999954.0,
"min": 49892.0,
"max": 1999954.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.427133560180664,
"min": 0.11474370956420898,
"max": 2.509345531463623,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1456.2801513671875,
"min": 13.769245147705078,
"max": 1543.7474365234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7041065924366317,
"min": 1.8926009489844242,
"max": 3.9966097904033346,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2222.463955461979,
"min": 227.1121138781309,
"max": 2437.9319721460342,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7041065924366317,
"min": 1.8926009489844242,
"max": 3.9966097904033346,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2222.463955461979,
"min": 227.1121138781309,
"max": 2437.9319721460342,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015580372259460596,
"min": 0.01440051540848799,
"max": 0.020561340373630325,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04674111677838179,
"min": 0.02905399630253669,
"max": 0.05670347951430206,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05260926079418924,
"min": 0.023284065661331017,
"max": 0.05887321788403723,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15782778238256773,
"min": 0.046568131322662035,
"max": 0.17661965365211169,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7065487645166603e-06,
"min": 3.7065487645166603e-06,
"max": 0.00029537542654152504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1119646293549981e-05,
"min": 1.1119646293549981e-05,
"max": 0.0008442630185789999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123548333333332,
"min": 0.10123548333333332,
"max": 0.19845847500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30370644999999996,
"min": 0.20760394999999995,
"max": 0.5814210000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.165061833333326e-05,
"min": 7.165061833333326e-05,
"max": 0.0049230779025000015,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021495185499999976,
"min": 0.00021495185499999976,
"max": 0.0140729079,
"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": "1732486749",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1732490940"
},
"total": 4191.220247088,
"count": 1,
"self": 0.5439462580006875,
"children": {
"run_training.setup": {
"total": 0.06735718999999563,
"count": 1,
"self": 0.06735718999999563
},
"TrainerController.start_learning": {
"total": 4190.60894364,
"count": 1,
"self": 7.323968403970866,
"children": {
"TrainerController._reset_env": {
"total": 6.97358056600001,
"count": 1,
"self": 6.97358056600001
},
"TrainerController.advance": {
"total": 4176.208930232029,
"count": 232752,
"self": 6.693358685079147,
"children": {
"env_step": {
"total": 2552.4196958649263,
"count": 232752,
"self": 2113.5019397118867,
"children": {
"SubprocessEnvManager._take_step": {
"total": 434.4520376279535,
"count": 232752,
"self": 24.407678135909464,
"children": {
"TorchPolicy.evaluate": {
"total": 410.044359492044,
"count": 222970,
"self": 410.044359492044
}
}
},
"workers": {
"total": 4.465718525086146,
"count": 232752,
"self": 0.0,
"children": {
"worker_root": {
"total": 4180.2349720020275,
"count": 232752,
"is_parallel": true,
"self": 2475.854468483971,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008969980000017586,
"count": 1,
"is_parallel": true,
"self": 0.00021829700000353114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006787009999982274,
"count": 2,
"is_parallel": true,
"self": 0.0006787009999982274
}
}
},
"UnityEnvironment.step": {
"total": 0.034051520000019764,
"count": 1,
"is_parallel": true,
"self": 0.0004902599999923041,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020821500001488857,
"count": 1,
"is_parallel": true,
"self": 0.00020821500001488857
},
"communicator.exchange": {
"total": 0.03239465100000416,
"count": 1,
"is_parallel": true,
"self": 0.03239465100000416
},
"steps_from_proto": {
"total": 0.0009583940000084112,
"count": 1,
"is_parallel": true,
"self": 0.00024582700004316393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007125669999652473,
"count": 2,
"is_parallel": true,
"self": 0.0007125669999652473
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1704.3805035180565,
"count": 232751,
"is_parallel": true,
"self": 51.024345080828425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 101.12958529816848,
"count": 232751,
"is_parallel": true,
"self": 101.12958529816848
},
"communicator.exchange": {
"total": 1429.2326786150902,
"count": 232751,
"is_parallel": true,
"self": 1429.2326786150902
},
"steps_from_proto": {
"total": 122.99389452396935,
"count": 232751,
"is_parallel": true,
"self": 40.63358166889472,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.36031285507462,
"count": 465502,
"is_parallel": true,
"self": 82.36031285507462
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1617.0958756820232,
"count": 232752,
"self": 10.845754111034921,
"children": {
"process_trajectory": {
"total": 247.96754633298664,
"count": 232752,
"self": 246.84349007498733,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1240562579993139,
"count": 10,
"self": 1.1240562579993139
}
}
},
"_update_policy": {
"total": 1358.2825752380018,
"count": 97,
"self": 328.4872574929875,
"children": {
"TorchPPOOptimizer.update": {
"total": 1029.7953177450142,
"count": 2910,
"self": 1029.7953177450142
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1329993867548183e-06,
"count": 1,
"self": 1.1329993867548183e-06
},
"TrainerController._save_models": {
"total": 0.10246330500012846,
"count": 1,
"self": 0.002496109000276192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09996719599985227,
"count": 1,
"self": 0.09996719599985227
}
}
}
}
}
}
}