ppo-Huggy / run_logs /timers.json
kaylinsiang's picture
Huggy
75fb48a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4120209217071533,
"min": 1.4120209217071533,
"max": 1.4327244758605957,
"count": 31
},
"Huggy.Policy.Entropy.sum": {
"value": 70561.5078125,
"min": 68961.3203125,
"max": 78404.84375,
"count": 31
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.4560327198364,
"min": 96.7265625,
"max": 428.6694915254237,
"count": 31
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49612.0,
"min": 48869.0,
"max": 50583.0,
"count": 31
},
"Huggy.Step.mean": {
"value": 1549602.0,
"min": 49952.0,
"max": 1549602.0,
"count": 31
},
"Huggy.Step.sum": {
"value": 1549602.0,
"min": 49952.0,
"max": 1549602.0,
"count": 31
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.330993890762329,
"min": 0.15775850415229797,
"max": 2.361525297164917,
"count": 31
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1139.85595703125,
"min": 18.457744598388672,
"max": 1172.370849609375,
"count": 31
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6398955377576785,
"min": 1.506448774256258,
"max": 3.8764252877897687,
"count": 31
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1779.9089179635048,
"min": 176.25450658798218,
"max": 1861.7355243861675,
"count": 31
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6398955377576785,
"min": 1.506448774256258,
"max": 3.8764252877897687,
"count": 31
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1779.9089179635048,
"min": 176.25450658798218,
"max": 1861.7355243861675,
"count": 31
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016863173224555793,
"min": 0.013562514287089773,
"max": 0.02078830281776997,
"count": 31
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05058951967366738,
"min": 0.027125028574179547,
"max": 0.06009566198141936,
"count": 31
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04836199316713544,
"min": 0.019457329219828047,
"max": 0.06140356156975031,
"count": 31
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14508597950140634,
"min": 0.038914658439656094,
"max": 0.17543674434224765,
"count": 31
},
"Huggy.Policy.LearningRate.mean": {
"value": 7.13836262054833e-05,
"min": 7.13836262054833e-05,
"max": 0.0002953242015585999,
"count": 31
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00021415087861644991,
"min": 0.00015815324728229996,
"max": 0.0008440272186575997,
"count": 31
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.12379451666666667,
"min": 0.12379451666666667,
"max": 0.1984414,
"count": 31
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.37138355,
"min": 0.25271770000000005,
"max": 0.5813424000000001,
"count": 31
},
"Huggy.Policy.Beta.mean": {
"value": 0.0011973463816666668,
"min": 0.0011973463816666668,
"max": 0.004922225860000001,
"count": 31
},
"Huggy.Policy.Beta.sum": {
"value": 0.0035920391450000003,
"min": 0.0026506132300000004,
"max": 0.01406898576,
"count": 31
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 31
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 31
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740492183",
"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=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": "1740494255"
},
"total": 2072.015205375,
"count": 1,
"self": 0.5979882619994896,
"children": {
"run_training.setup": {
"total": 0.022745536000002176,
"count": 1,
"self": 0.022745536000002176
},
"TrainerController.start_learning": {
"total": 2071.3944715770003,
"count": 1,
"self": 3.7777173940648936,
"children": {
"TrainerController._reset_env": {
"total": 2.915135300999964,
"count": 1,
"self": 2.915135300999964
},
"TrainerController.advance": {
"total": 2064.4040634369353,
"count": 179644,
"self": 4.181555508057954,
"children": {
"env_step": {
"total": 1676.4948526358905,
"count": 179644,
"self": 1309.1960653978272,
"children": {
"SubprocessEnvManager._take_step": {
"total": 364.9165113710998,
"count": 179644,
"self": 13.192431799040492,
"children": {
"TorchPolicy.evaluate": {
"total": 351.7240795720593,
"count": 173568,
"self": 351.7240795720593
}
}
},
"workers": {
"total": 2.3822758669634823,
"count": 179643,
"self": 0.0,
"children": {
"worker_root": {
"total": 2064.932116998956,
"count": 179643,
"is_parallel": true,
"self": 1000.6710110899389,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010934919999954218,
"count": 1,
"is_parallel": true,
"self": 0.0003954530000100931,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006980389999853287,
"count": 2,
"is_parallel": true,
"self": 0.0006980389999853287
}
}
},
"UnityEnvironment.step": {
"total": 0.03103269400003228,
"count": 1,
"is_parallel": true,
"self": 0.0003062779999254417,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000187716000027649,
"count": 1,
"is_parallel": true,
"self": 0.000187716000027649
},
"communicator.exchange": {
"total": 0.029836290000048393,
"count": 1,
"is_parallel": true,
"self": 0.029836290000048393
},
"steps_from_proto": {
"total": 0.0007024100000307953,
"count": 1,
"is_parallel": true,
"self": 0.00021234199994069058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004900680000901048,
"count": 2,
"is_parallel": true,
"self": 0.0004900680000901048
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1064.2611059090173,
"count": 179642,
"is_parallel": true,
"self": 31.336347165933148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 69.5594167570705,
"count": 179642,
"is_parallel": true,
"self": 69.5594167570705
},
"communicator.exchange": {
"total": 889.0715710029657,
"count": 179642,
"is_parallel": true,
"self": 889.0715710029657
},
"steps_from_proto": {
"total": 74.2937709830478,
"count": 179642,
"is_parallel": true,
"self": 27.882938830227204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 46.4108321528206,
"count": 359284,
"is_parallel": true,
"self": 46.4108321528206
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 383.7276552929867,
"count": 179643,
"self": 5.772488416927558,
"children": {
"process_trajectory": {
"total": 128.37741301206097,
"count": 179643,
"self": 127.32936584406093,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0480471680000392,
"count": 7,
"self": 1.0480471680000392
}
}
},
"_update_policy": {
"total": 249.57775386399817,
"count": 75,
"self": 198.1252474599977,
"children": {
"TorchPPOOptimizer.update": {
"total": 51.452506404000474,
"count": 2250,
"self": 51.452506404000474
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.624000105948653e-06,
"count": 1,
"self": 1.624000105948653e-06
},
"TrainerController._save_models": {
"total": 0.2975538210002924,
"count": 1,
"self": 0.0035846290002155,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2939691920000769,
"count": 1,
"self": 0.2939691920000769
}
}
}
}
}
}
}