ppo-Huggy / run_logs /timers.json
Mehdikarim's picture
Huggy
1a33b6e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4029141664505005,
"min": 1.4029141664505005,
"max": 1.4263463020324707,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70273.375,
"min": 69034.9296875,
"max": 77989.25,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.01221374045801,
"min": 72.03654970760233,
"max": 405.8780487804878,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49788.0,
"min": 48972.0,
"max": 50365.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999765.0,
"min": 49965.0,
"max": 1999765.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999765.0,
"min": 49965.0,
"max": 1999765.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.543781280517578,
"min": 0.11719433218240738,
"max": 2.543781280517578,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1666.1767578125,
"min": 14.297708511352539,
"max": 1692.832275390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.05650748369348,
"min": 1.8017162863836913,
"max": 4.05650748369348,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2657.012401819229,
"min": 219.80938693881035,
"max": 2679.4396778941154,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.05650748369348,
"min": 1.8017162863836913,
"max": 4.05650748369348,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2657.012401819229,
"min": 219.80938693881035,
"max": 2679.4396778941154,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0214598090948938,
"min": 0.013242440628043065,
"max": 0.0214598090948938,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0643794272846814,
"min": 0.02648488125608613,
"max": 0.0643794272846814,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056223598950439026,
"min": 0.022164357360452414,
"max": 0.06328142030785482,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16867079685131708,
"min": 0.04432871472090483,
"max": 0.18167228202025096,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8442487186166555e-06,
"min": 3.8442487186166555e-06,
"max": 0.00029529277656907495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1532746155849967e-05,
"min": 1.1532746155849967e-05,
"max": 0.0008438236687254501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128138333333335,
"min": 0.10128138333333335,
"max": 0.19843092500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30384415000000004,
"min": 0.2076865,
"max": 0.58127455,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.394102833333317e-05,
"min": 7.394102833333317e-05,
"max": 0.0049217031574999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002218230849999995,
"min": 0.0002218230849999995,
"max": 0.014065600045,
"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": "1743617314",
"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": "1743619881"
},
"total": 2566.4802646109997,
"count": 1,
"self": 0.44003590500005885,
"children": {
"run_training.setup": {
"total": 0.022477140000091822,
"count": 1,
"self": 0.022477140000091822
},
"TrainerController.start_learning": {
"total": 2566.017751566,
"count": 1,
"self": 4.683763831037595,
"children": {
"TrainerController._reset_env": {
"total": 2.981801293999979,
"count": 1,
"self": 2.981801293999979
},
"TrainerController.advance": {
"total": 2558.213592526962,
"count": 233238,
"self": 4.779114258948084,
"children": {
"env_step": {
"total": 2061.394272871045,
"count": 233238,
"self": 1618.0012953019454,
"children": {
"SubprocessEnvManager._take_step": {
"total": 440.51601931399034,
"count": 233238,
"self": 16.891743600003792,
"children": {
"TorchPolicy.evaluate": {
"total": 423.62427571398655,
"count": 222882,
"self": 423.62427571398655
}
}
},
"workers": {
"total": 2.8769582551090025,
"count": 233238,
"self": 0.0,
"children": {
"worker_root": {
"total": 2557.86474031714,
"count": 233238,
"is_parallel": true,
"self": 1240.3679049510501,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014200169999867285,
"count": 1,
"is_parallel": true,
"self": 0.00046600900009252655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009540079998942019,
"count": 2,
"is_parallel": true,
"self": 0.0009540079998942019
}
}
},
"UnityEnvironment.step": {
"total": 0.0314125590000458,
"count": 1,
"is_parallel": true,
"self": 0.0003444820001732296,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021896499993090401,
"count": 1,
"is_parallel": true,
"self": 0.00021896499993090401
},
"communicator.exchange": {
"total": 0.029966618999992534,
"count": 1,
"is_parallel": true,
"self": 0.029966618999992534
},
"steps_from_proto": {
"total": 0.000882492999949136,
"count": 1,
"is_parallel": true,
"self": 0.0002258869999423041,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006566060000068319,
"count": 2,
"is_parallel": true,
"self": 0.0006566060000068319
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1317.4968353660897,
"count": 233237,
"is_parallel": true,
"self": 37.85977503726053,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.05409544592192,
"count": 233237,
"is_parallel": true,
"self": 86.05409544592192
},
"communicator.exchange": {
"total": 1103.2121512720064,
"count": 233237,
"is_parallel": true,
"self": 1103.2121512720064
},
"steps_from_proto": {
"total": 90.37081361090088,
"count": 233237,
"is_parallel": true,
"self": 33.674328668854855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.69648494204603,
"count": 466474,
"is_parallel": true,
"self": 56.69648494204603
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 492.0402053969691,
"count": 233238,
"self": 7.163893781939123,
"children": {
"process_trajectory": {
"total": 181.9348881490322,
"count": 233238,
"self": 180.48279722603286,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4520909229993322,
"count": 10,
"self": 1.4520909229993322
}
}
},
"_update_policy": {
"total": 302.9414234659978,
"count": 97,
"self": 238.86617795601092,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.07524550998687,
"count": 2910,
"self": 64.07524550998687
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.315999725193251e-06,
"count": 1,
"self": 1.315999725193251e-06
},
"TrainerController._save_models": {
"total": 0.13859259800028667,
"count": 1,
"self": 0.0019117120000373689,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1366808860002493,
"count": 1,
"self": 0.1366808860002493
}
}
}
}
}
}
}