ppo-Huggy / run_logs /timers.json
xmustu's picture
Huggy
f53448d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4097697734832764,
"min": 1.4097697734832764,
"max": 1.4299544095993042,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69876.6484375,
"min": 68384.3125,
"max": 78242.4453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.4054054054054,
"min": 79.28501628664495,
"max": 396.40944881889766,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49376.0,
"min": 48681.0,
"max": 50344.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999957.0,
"min": 49933.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999957.0,
"min": 49933.0,
"max": 1999957.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5144171714782715,
"min": 0.18214495480060577,
"max": 2.528886318206787,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1488.534912109375,
"min": 22.95026397705078,
"max": 1540.091796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8808193142349654,
"min": 1.9803102082676358,
"max": 4.008439526044203,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2297.4450340270996,
"min": 249.5190862417221,
"max": 2424.1984788179398,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8808193142349654,
"min": 1.9803102082676358,
"max": 4.008439526044203,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2297.4450340270996,
"min": 249.5190862417221,
"max": 2424.1984788179398,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01778793147295801,
"min": 0.01268079763200755,
"max": 0.01966668230791887,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053363794418874025,
"min": 0.0253615952640151,
"max": 0.05816973711480386,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.062162778981857826,
"min": 0.020725850543628136,
"max": 0.062162778981857826,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18648833694557349,
"min": 0.04145170108725627,
"max": 0.18648833694557349,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7864487378833274e-06,
"min": 3.7864487378833274e-06,
"max": 0.00029537467654177496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1359346213649982e-05,
"min": 1.1359346213649982e-05,
"max": 0.00084441496852835,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126211666666668,
"min": 0.10126211666666668,
"max": 0.198458225,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30378635000000004,
"min": 0.20765415000000007,
"max": 0.5814716499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.297962166666657e-05,
"min": 7.297962166666657e-05,
"max": 0.0049230654275,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021893886499999973,
"min": 0.00021893886499999973,
"max": 0.014075435335,
"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": "1723001230",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723003700"
},
"total": 2469.833633094,
"count": 1,
"self": 0.43653709499994875,
"children": {
"run_training.setup": {
"total": 0.062355020000040895,
"count": 1,
"self": 0.062355020000040895
},
"TrainerController.start_learning": {
"total": 2469.334740979,
"count": 1,
"self": 4.460023657878082,
"children": {
"TrainerController._reset_env": {
"total": 2.839277839000033,
"count": 1,
"self": 2.839277839000033
},
"TrainerController.advance": {
"total": 2461.910511728121,
"count": 232251,
"self": 4.7970884551550625,
"children": {
"env_step": {
"total": 1961.6164572980251,
"count": 232251,
"self": 1614.0965608670522,
"children": {
"SubprocessEnvManager._take_step": {
"total": 344.5018383091199,
"count": 232251,
"self": 18.645904774145833,
"children": {
"TorchPolicy.evaluate": {
"total": 325.85593353497404,
"count": 222942,
"self": 325.85593353497404
}
}
},
"workers": {
"total": 3.0180581218529596,
"count": 232251,
"self": 0.0,
"children": {
"worker_root": {
"total": 2461.8480955270356,
"count": 232251,
"is_parallel": true,
"self": 1156.0325513071,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010896189999130002,
"count": 1,
"is_parallel": true,
"self": 0.0002666950000502766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008229239998627236,
"count": 2,
"is_parallel": true,
"self": 0.0008229239998627236
}
}
},
"UnityEnvironment.step": {
"total": 0.03063758999996935,
"count": 1,
"is_parallel": true,
"self": 0.00038950499993006815,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021316599998044694,
"count": 1,
"is_parallel": true,
"self": 0.00021316599998044694
},
"communicator.exchange": {
"total": 0.029292851000036535,
"count": 1,
"is_parallel": true,
"self": 0.029292851000036535
},
"steps_from_proto": {
"total": 0.0007420680000223001,
"count": 1,
"is_parallel": true,
"self": 0.00018849599996428879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005535720000580113,
"count": 2,
"is_parallel": true,
"self": 0.0005535720000580113
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1305.8155442199356,
"count": 232250,
"is_parallel": true,
"self": 38.995702575025234,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.89529822795828,
"count": 232250,
"is_parallel": true,
"self": 83.89529822795828
},
"communicator.exchange": {
"total": 1089.384624970977,
"count": 232250,
"is_parallel": true,
"self": 1089.384624970977
},
"steps_from_proto": {
"total": 93.53991844597522,
"count": 232250,
"is_parallel": true,
"self": 35.05045034192756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.48946810404766,
"count": 464500,
"is_parallel": true,
"self": 58.48946810404766
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 495.49696597494085,
"count": 232251,
"self": 6.8570108959761455,
"children": {
"process_trajectory": {
"total": 160.12825170396457,
"count": 232251,
"self": 158.7215560689641,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4066956350004602,
"count": 10,
"self": 1.4066956350004602
}
}
},
"_update_policy": {
"total": 328.51170337500014,
"count": 97,
"self": 264.90308621000054,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.6086171649996,
"count": 2910,
"self": 63.6086171649996
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.330002856382634e-07,
"count": 1,
"self": 8.330002856382634e-07
},
"TrainerController._save_models": {
"total": 0.12492692100022396,
"count": 1,
"self": 0.002066136000394181,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12286078499982978,
"count": 1,
"self": 0.12286078499982978
}
}
}
}
}
}
}