ppo-Huggy / run_logs /timers.json
dfomin's picture
Huggy
8f97d2e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4021506309509277,
"min": 1.4021506309509277,
"max": 1.4292103052139282,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70972.65625,
"min": 68927.1875,
"max": 77306.6484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 88.6678445229682,
"min": 88.6678445229682,
"max": 379.9469696969697,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50186.0,
"min": 48751.0,
"max": 50204.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49535.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49535.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3029184341430664,
"min": 0.02671789564192295,
"max": 2.428316116333008,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1301.14892578125,
"min": 3.500044345855713,
"max": 1301.730712890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.584758006682438,
"min": 1.7351463882977727,
"max": 3.924694079075367,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2025.3882737755775,
"min": 227.3041768670082,
"max": 2049.1136340498924,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.584758006682438,
"min": 1.7351463882977727,
"max": 3.924694079075367,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2025.3882737755775,
"min": 227.3041768670082,
"max": 2049.1136340498924,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017674103040755857,
"min": 0.01357571230425189,
"max": 0.02055608203809243,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053022309122267575,
"min": 0.02715142460850378,
"max": 0.057471207954222336,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04834068790078164,
"min": 0.023385259291778007,
"max": 0.05616339910775423,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1450220637023449,
"min": 0.04677051858355601,
"max": 0.16414619100590547,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4437988520999935e-06,
"min": 3.4437988520999935e-06,
"max": 0.000295333126555625,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.033139655629998e-05,
"min": 1.033139655629998e-05,
"max": 0.0008441562186145997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011479,
"min": 0.1011479,
"max": 0.19844437500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034437,
"min": 0.2074295,
"max": 0.5813853999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.72802099999999e-05,
"min": 6.72802099999999e-05,
"max": 0.0049223743125,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002018406299999997,
"min": 0.0002018406299999997,
"max": 0.014071131459999997,
"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": "1686599097",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1686601900"
},
"total": 2802.986907198,
"count": 1,
"self": 0.45040726000024733,
"children": {
"run_training.setup": {
"total": 0.04528841799992733,
"count": 1,
"self": 0.04528841799992733
},
"TrainerController.start_learning": {
"total": 2802.49121152,
"count": 1,
"self": 5.611448853102502,
"children": {
"TrainerController._reset_env": {
"total": 6.367940013999942,
"count": 1,
"self": 6.367940013999942
},
"TrainerController.advance": {
"total": 2790.384196418898,
"count": 231772,
"self": 5.392480041847193,
"children": {
"env_step": {
"total": 2189.031861622014,
"count": 231772,
"self": 1841.5863196628761,
"children": {
"SubprocessEnvManager._take_step": {
"total": 343.85337579196937,
"count": 231772,
"self": 19.63330931596124,
"children": {
"TorchPolicy.evaluate": {
"total": 324.2200664760081,
"count": 223011,
"self": 324.2200664760081
}
}
},
"workers": {
"total": 3.592166167168216,
"count": 231772,
"self": 0.0,
"children": {
"worker_root": {
"total": 2793.158551498107,
"count": 231772,
"is_parallel": true,
"self": 1294.3858166680209,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009994729999789342,
"count": 1,
"is_parallel": true,
"self": 0.0002878129999999146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007116599999790196,
"count": 2,
"is_parallel": true,
"self": 0.0007116599999790196
}
}
},
"UnityEnvironment.step": {
"total": 0.0631636510000817,
"count": 1,
"is_parallel": true,
"self": 0.0003696980000995609,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026598700003432896,
"count": 1,
"is_parallel": true,
"self": 0.00026598700003432896
},
"communicator.exchange": {
"total": 0.061639950999961,
"count": 1,
"is_parallel": true,
"self": 0.061639950999961
},
"steps_from_proto": {
"total": 0.0008880149999868081,
"count": 1,
"is_parallel": true,
"self": 0.00027516199997990043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006128530000069077,
"count": 2,
"is_parallel": true,
"self": 0.0006128530000069077
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1498.7727348300862,
"count": 231771,
"is_parallel": true,
"self": 44.13617942124256,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.22232466592834,
"count": 231771,
"is_parallel": true,
"self": 92.22232466592834
},
"communicator.exchange": {
"total": 1252.0732853139455,
"count": 231771,
"is_parallel": true,
"self": 1252.0732853139455
},
"steps_from_proto": {
"total": 110.34094542896969,
"count": 231771,
"is_parallel": true,
"self": 40.49386836106339,
"children": {
"_process_rank_one_or_two_observation": {
"total": 69.8470770679063,
"count": 463542,
"is_parallel": true,
"self": 69.8470770679063
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 595.959854755037,
"count": 231772,
"self": 8.378176170927304,
"children": {
"process_trajectory": {
"total": 153.5555437591089,
"count": 231772,
"self": 152.03240291410884,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5231408450000572,
"count": 10,
"self": 1.5231408450000572
}
}
},
"_update_policy": {
"total": 434.0261348250008,
"count": 97,
"self": 369.65020447800055,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.37593034700024,
"count": 2910,
"self": 64.37593034700024
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1759998415072914e-06,
"count": 1,
"self": 1.1759998415072914e-06
},
"TrainerController._save_models": {
"total": 0.1276250579999214,
"count": 1,
"self": 0.002182446999995591,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12544261099992582,
"count": 1,
"self": 0.12544261099992582
}
}
}
}
}
}
}