ppo-Huggy / run_logs /timers.json
satcos's picture
Huggy
9c3381b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4111100435256958,
"min": 1.4111100435256958,
"max": 1.4283759593963623,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71455.7890625,
"min": 67090.2890625,
"max": 75498.4140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.04339250493096,
"min": 88.47763864042933,
"max": 385.84615384615387,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49708.0,
"min": 48871.0,
"max": 50160.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999503.0,
"min": 49540.0,
"max": 1999503.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999503.0,
"min": 49540.0,
"max": 1999503.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.389478921890259,
"min": 0.13294769823551178,
"max": 2.4315483570098877,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1211.4658203125,
"min": 17.150253295898438,
"max": 1359.235595703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6292522757716434,
"min": 1.7493224541346233,
"max": 3.9349686508057875,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1840.0309038162231,
"min": 225.6625965833664,
"max": 2114.083960235119,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6292522757716434,
"min": 1.7493224541346233,
"max": 3.9349686508057875,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1840.0309038162231,
"min": 225.6625965833664,
"max": 2114.083960235119,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01636572327590026,
"min": 0.013811558539358278,
"max": 0.02016613746139531,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04909716982770078,
"min": 0.027623117078716557,
"max": 0.05859324663373021,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05041910376813677,
"min": 0.02235317944238583,
"max": 0.06008126462499301,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1512573113044103,
"min": 0.04470635888477166,
"max": 0.17688050928215188,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3555488815166703e-06,
"min": 3.3555488815166703e-06,
"max": 0.0002953483515505499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0066646644550011e-05,
"min": 1.0066646644550011e-05,
"max": 0.0008439814686728499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111848333333336,
"min": 0.10111848333333336,
"max": 0.19844945000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033554500000001,
"min": 0.20738795000000004,
"max": 0.5813271499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.581231833333342e-05,
"min": 6.581231833333342e-05,
"max": 0.0049226275550000006,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019743695500000028,
"min": 0.00019743695500000028,
"max": 0.014068224785000003,
"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": "1702377441",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702379824"
},
"total": 2382.938202666,
"count": 1,
"self": 0.7514797179997004,
"children": {
"run_training.setup": {
"total": 0.05943241299996771,
"count": 1,
"self": 0.05943241299996771
},
"TrainerController.start_learning": {
"total": 2382.127290535,
"count": 1,
"self": 4.403496192064722,
"children": {
"TrainerController._reset_env": {
"total": 4.231646531000024,
"count": 1,
"self": 4.231646531000024
},
"TrainerController.advance": {
"total": 2373.350643728935,
"count": 232041,
"self": 4.619798269011426,
"children": {
"env_step": {
"total": 1873.7692213918494,
"count": 232041,
"self": 1547.564660063769,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.46904969010654,
"count": 232041,
"self": 17.206760349029196,
"children": {
"TorchPolicy.evaluate": {
"total": 306.26228934107735,
"count": 223020,
"self": 306.26228934107735
}
}
},
"workers": {
"total": 2.7355116379739,
"count": 232041,
"self": 0.0,
"children": {
"worker_root": {
"total": 2374.3397051720613,
"count": 232041,
"is_parallel": true,
"self": 1122.305286819099,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008503979998977229,
"count": 1,
"is_parallel": true,
"self": 0.00023968499988313852,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006107130000145844,
"count": 2,
"is_parallel": true,
"self": 0.0006107130000145844
}
}
},
"UnityEnvironment.step": {
"total": 0.03181086300003244,
"count": 1,
"is_parallel": true,
"self": 0.00030165199996190495,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002249990000109392,
"count": 1,
"is_parallel": true,
"self": 0.0002249990000109392
},
"communicator.exchange": {
"total": 0.030567804000042997,
"count": 1,
"is_parallel": true,
"self": 0.030567804000042997
},
"steps_from_proto": {
"total": 0.0007164080000165995,
"count": 1,
"is_parallel": true,
"self": 0.00020730800008550432,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005090999999310952,
"count": 2,
"is_parallel": true,
"self": 0.0005090999999310952
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1252.0344183529623,
"count": 232040,
"is_parallel": true,
"self": 39.23334904290505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.97137331094655,
"count": 232040,
"is_parallel": true,
"self": 80.97137331094655
},
"communicator.exchange": {
"total": 1043.1249701381416,
"count": 232040,
"is_parallel": true,
"self": 1043.1249701381416
},
"steps_from_proto": {
"total": 88.704725860969,
"count": 232040,
"is_parallel": true,
"self": 30.966123377961708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.7386024830073,
"count": 464080,
"is_parallel": true,
"self": 57.7386024830073
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.96162406807446,
"count": 232041,
"self": 6.778370245990118,
"children": {
"process_trajectory": {
"total": 150.44197057708413,
"count": 232041,
"self": 149.25562533208347,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1863452450006662,
"count": 10,
"self": 1.1863452450006662
}
}
},
"_update_policy": {
"total": 337.7412832450002,
"count": 97,
"self": 274.3771379119876,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.36414533301263,
"count": 2910,
"self": 63.36414533301263
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1910001376236323e-06,
"count": 1,
"self": 1.1910001376236323e-06
},
"TrainerController._save_models": {
"total": 0.14150289200006227,
"count": 1,
"self": 0.002409850000276492,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13909304199978578,
"count": 1,
"self": 0.13909304199978578
}
}
}
}
}
}
}