ppo-Huggy / run_logs /timers.json
sahiljasani's picture
Huggy
15c1894 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030367136001587,
"min": 1.4030367136001587,
"max": 1.426857829093933,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70324.40625,
"min": 69119.6796875,
"max": 77381.359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.71863117870723,
"min": 78.63022508038586,
"max": 391.703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48770.0,
"min": 48770.0,
"max": 50138.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999897.0,
"min": 49597.0,
"max": 1999897.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999897.0,
"min": 49597.0,
"max": 1999897.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.461026668548584,
"min": 0.22025302052497864,
"max": 2.48207950592041,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1294.5,
"min": 27.97213363647461,
"max": 1551.2996826171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8814870285670566,
"min": 1.8454191137955884,
"max": 3.9268100823735597,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2041.6621770262718,
"min": 234.36822745203972,
"max": 2444.762258529663,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8814870285670566,
"min": 1.8454191137955884,
"max": 3.9268100823735597,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2041.6621770262718,
"min": 234.36822745203972,
"max": 2444.762258529663,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01703993510939957,
"min": 0.01208885180191525,
"max": 0.01980335939054688,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0511198053281987,
"min": 0.0241777036038305,
"max": 0.058098418901984895,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05490947431988186,
"min": 0.019271769654005767,
"max": 0.05887120782087246,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16472842295964557,
"min": 0.038543539308011535,
"max": 0.169488608588775,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3375988874999933e-06,
"min": 3.3375988874999933e-06,
"max": 0.00029536245154585,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.001279666249998e-05,
"min": 1.001279666249998e-05,
"max": 0.0008440665186444998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111250000000001,
"min": 0.10111250000000001,
"max": 0.19845415000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30333750000000004,
"min": 0.20738825000000005,
"max": 0.5813555,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.55137499999999e-05,
"min": 6.55137499999999e-05,
"max": 0.004922862085000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019654124999999968,
"min": 0.00019654124999999968,
"max": 0.01406963945,
"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": "1740335357",
"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": "1740337819"
},
"total": 2462.4570359540003,
"count": 1,
"self": 0.4358521560002373,
"children": {
"run_training.setup": {
"total": 0.02398476700000174,
"count": 1,
"self": 0.02398476700000174
},
"TrainerController.start_learning": {
"total": 2461.997199031,
"count": 1,
"self": 4.515842456981773,
"children": {
"TrainerController._reset_env": {
"total": 2.9952464950000603,
"count": 1,
"self": 2.9952464950000603
},
"TrainerController.advance": {
"total": 2454.3738031610183,
"count": 232706,
"self": 4.896361451854318,
"children": {
"env_step": {
"total": 1968.6910363991399,
"count": 232706,
"self": 1543.333552732214,
"children": {
"SubprocessEnvManager._take_step": {
"total": 422.6876460239797,
"count": 232706,
"self": 15.786174560988911,
"children": {
"TorchPolicy.evaluate": {
"total": 406.9014714629908,
"count": 223058,
"self": 406.9014714629908
}
}
},
"workers": {
"total": 2.669837642946163,
"count": 232706,
"self": 0.0,
"children": {
"worker_root": {
"total": 2454.422054016024,
"count": 232706,
"is_parallel": true,
"self": 1199.8635993700827,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011207759999933842,
"count": 1,
"is_parallel": true,
"self": 0.0003193649998820547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008014110001113295,
"count": 2,
"is_parallel": true,
"self": 0.0008014110001113295
}
}
},
"UnityEnvironment.step": {
"total": 0.02853049700001975,
"count": 1,
"is_parallel": true,
"self": 0.00032176100000924635,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020405700001902005,
"count": 1,
"is_parallel": true,
"self": 0.00020405700001902005
},
"communicator.exchange": {
"total": 0.027280796000013652,
"count": 1,
"is_parallel": true,
"self": 0.027280796000013652
},
"steps_from_proto": {
"total": 0.0007238829999778318,
"count": 1,
"is_parallel": true,
"self": 0.0001987260000078095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005251569999700223,
"count": 2,
"is_parallel": true,
"self": 0.0005251569999700223
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1254.5584546459413,
"count": 232705,
"is_parallel": true,
"self": 37.402009112939595,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.24261121300788,
"count": 232705,
"is_parallel": true,
"self": 82.24261121300788
},
"communicator.exchange": {
"total": 1046.5433523210286,
"count": 232705,
"is_parallel": true,
"self": 1046.5433523210286
},
"steps_from_proto": {
"total": 88.37048199896515,
"count": 232705,
"is_parallel": true,
"self": 33.02064862690111,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.34983337206404,
"count": 465410,
"is_parallel": true,
"self": 55.34983337206404
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 480.78640531002407,
"count": 232706,
"self": 6.663920749056388,
"children": {
"process_trajectory": {
"total": 169.13737811296664,
"count": 232706,
"self": 167.8643152119671,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2730629009995482,
"count": 10,
"self": 1.2730629009995482
}
}
},
"_update_policy": {
"total": 304.98510644800103,
"count": 97,
"self": 240.7413360650005,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.24377038300054,
"count": 2910,
"self": 64.24377038300054
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1150000318593811e-06,
"count": 1,
"self": 1.1150000318593811e-06
},
"TrainerController._save_models": {
"total": 0.1123058029997992,
"count": 1,
"self": 0.0018239039995933126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11048189900020589,
"count": 1,
"self": 0.11048189900020589
}
}
}
}
}
}
}