ppo-Huggy / run_logs /timers.json
Yaman42's picture
Huggy
18352e0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4015576839447021,
"min": 1.4015576839447021,
"max": 1.4253987073898315,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71776.5703125,
"min": 68994.5234375,
"max": 77455.078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.24593128390596,
"min": 74.3795731707317,
"max": 394.6796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49353.0,
"min": 48793.0,
"max": 50519.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999732.0,
"min": 49897.0,
"max": 1999732.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999732.0,
"min": 49897.0,
"max": 1999732.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4849510192871094,
"min": 0.04613793268799782,
"max": 2.5020205974578857,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1374.177978515625,
"min": 5.859517574310303,
"max": 1571.0501708984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.881715062729489,
"min": 1.8323517258711688,
"max": 4.0334273550967525,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2146.5884296894073,
"min": 232.70866918563843,
"max": 2438.7107147574425,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.881715062729489,
"min": 1.8323517258711688,
"max": 4.0334273550967525,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2146.5884296894073,
"min": 232.70866918563843,
"max": 2438.7107147574425,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016583039207681498,
"min": 0.013244869614815495,
"max": 0.019006201834417882,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04974911762304449,
"min": 0.02648973922963099,
"max": 0.054710469148994884,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056615272412697475,
"min": 0.022358821829160054,
"max": 0.06275592967867852,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16984581723809242,
"min": 0.04471764365832011,
"max": 0.1875464829305808,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6976487674833377e-06,
"min": 3.6976487674833377e-06,
"max": 0.00029537835154054993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1092946302450013e-05,
"min": 1.1092946302450013e-05,
"max": 0.0008440101186633,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012325166666667,
"min": 0.1012325166666667,
"max": 0.19845945000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036975500000001,
"min": 0.20760950000000006,
"max": 0.5813367000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.150258166666674e-05,
"min": 7.150258166666674e-05,
"max": 0.004923126555000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021450774500000023,
"min": 0.00021450774500000023,
"max": 0.014068701329999999,
"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": "1740379030",
"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=Huggy42 --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": "1740381538"
},
"total": 2508.035474416,
"count": 1,
"self": 0.4343139870002233,
"children": {
"run_training.setup": {
"total": 0.02297801399981836,
"count": 1,
"self": 0.02297801399981836
},
"TrainerController.start_learning": {
"total": 2507.578182415,
"count": 1,
"self": 4.541044433073694,
"children": {
"TrainerController._reset_env": {
"total": 2.7950949979999677,
"count": 1,
"self": 2.7950949979999677
},
"TrainerController.advance": {
"total": 2500.113155521926,
"count": 233029,
"self": 4.66721216385622,
"children": {
"env_step": {
"total": 2014.334864300007,
"count": 233029,
"self": 1580.4285928999102,
"children": {
"SubprocessEnvManager._take_step": {
"total": 431.1449864849767,
"count": 233029,
"self": 16.334075461896646,
"children": {
"TorchPolicy.evaluate": {
"total": 414.81091102308005,
"count": 223084,
"self": 414.81091102308005
}
}
},
"workers": {
"total": 2.7612849151200862,
"count": 233029,
"self": 0.0,
"children": {
"worker_root": {
"total": 2499.814027111054,
"count": 233029,
"is_parallel": true,
"self": 1211.890819252948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009084830001029331,
"count": 1,
"is_parallel": true,
"self": 0.00024820300018291164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006602799999200215,
"count": 2,
"is_parallel": true,
"self": 0.0006602799999200215
}
}
},
"UnityEnvironment.step": {
"total": 0.03585916800011546,
"count": 1,
"is_parallel": true,
"self": 0.00031381999997392995,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002033640000718151,
"count": 1,
"is_parallel": true,
"self": 0.0002033640000718151
},
"communicator.exchange": {
"total": 0.034372611999970104,
"count": 1,
"is_parallel": true,
"self": 0.034372611999970104
},
"steps_from_proto": {
"total": 0.0009693720000996109,
"count": 1,
"is_parallel": true,
"self": 0.0002240559999791003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007453160001205106,
"count": 2,
"is_parallel": true,
"self": 0.0007453160001205106
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1287.9232078581063,
"count": 233028,
"is_parallel": true,
"self": 37.18562700012717,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.51615859404797,
"count": 233028,
"is_parallel": true,
"self": 84.51615859404797
},
"communicator.exchange": {
"total": 1076.5627890108897,
"count": 233028,
"is_parallel": true,
"self": 1076.5627890108897
},
"steps_from_proto": {
"total": 89.65863325304144,
"count": 233028,
"is_parallel": true,
"self": 33.714470253051786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.94416299998966,
"count": 466056,
"is_parallel": true,
"self": 55.94416299998966
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.1110790580626,
"count": 233029,
"self": 6.7584369140909075,
"children": {
"process_trajectory": {
"total": 168.8269627669731,
"count": 233029,
"self": 167.5150480229729,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3119147440002052,
"count": 10,
"self": 1.3119147440002052
}
}
},
"_update_policy": {
"total": 305.5256793769986,
"count": 97,
"self": 241.24161955900604,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.28405981799256,
"count": 2910,
"self": 64.28405981799256
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.470001375826541e-07,
"count": 1,
"self": 8.470001375826541e-07
},
"TrainerController._save_models": {
"total": 0.1288866150002832,
"count": 1,
"self": 0.0019434590003584162,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12694315599992478,
"count": 1,
"self": 0.12694315599992478
}
}
}
}
}
}
}