ppo-Huggy / run_logs /timers.json
keshav-kumar's picture
Huggy
e983a93 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4059911966323853,
"min": 1.4059911966323853,
"max": 1.4295859336853027,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71421.5390625,
"min": 68263.6640625,
"max": 77744.796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.54249547920433,
"min": 86.4021164021164,
"max": 364.18978102189783,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49517.0,
"min": 48990.0,
"max": 50302.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999320.0,
"min": 49847.0,
"max": 1999320.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999320.0,
"min": 49847.0,
"max": 1999320.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3802249431610107,
"min": 0.1874678134918213,
"max": 2.4597487449645996,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1316.264404296875,
"min": 25.495622634887695,
"max": 1361.802490234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6791436499756025,
"min": 1.843385948525632,
"max": 3.939546160330799,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2034.5664384365082,
"min": 250.70048899948597,
"max": 2139.829935312271,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6791436499756025,
"min": 1.843385948525632,
"max": 3.939546160330799,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2034.5664384365082,
"min": 250.70048899948597,
"max": 2139.829935312271,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018403770267226113,
"min": 0.012994076201478796,
"max": 0.021660750156782645,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.055211310801678334,
"min": 0.02598815240295759,
"max": 0.0609265881954343,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052571181539032195,
"min": 0.021495878427392905,
"max": 0.05778525012234847,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15771354461709658,
"min": 0.044175425358116624,
"max": 0.16019215968747935,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4386988537999906e-06,
"min": 3.4386988537999906e-06,
"max": 0.00029535990154669995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0316096561399971e-05,
"min": 1.0316096561399971e-05,
"max": 0.0008443335185555,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114619999999998,
"min": 0.10114619999999998,
"max": 0.19845329999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30343859999999995,
"min": 0.20743920000000002,
"max": 0.5814444999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.719537999999989e-05,
"min": 6.719537999999989e-05,
"max": 0.00492281967,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020158613999999965,
"min": 0.00020158613999999965,
"max": 0.01407408055,
"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": "1713236214",
"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=Huggy2 --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713240873"
},
"total": 4659.336699489,
"count": 1,
"self": 0.5937615040002129,
"children": {
"run_training.setup": {
"total": 0.069913182999926,
"count": 1,
"self": 0.069913182999926
},
"TrainerController.start_learning": {
"total": 4658.673024802,
"count": 1,
"self": 8.471103569009756,
"children": {
"TrainerController._reset_env": {
"total": 2.9790746300000137,
"count": 1,
"self": 2.9790746300000137
},
"TrainerController.advance": {
"total": 4647.10305646999,
"count": 232160,
"self": 8.73063031287711,
"children": {
"env_step": {
"total": 3049.6581565171455,
"count": 232160,
"self": 2540.2645308521523,
"children": {
"SubprocessEnvManager._take_step": {
"total": 503.86419173289073,
"count": 232160,
"self": 33.59927258573134,
"children": {
"TorchPolicy.evaluate": {
"total": 470.2649191471594,
"count": 222986,
"self": 470.2649191471594
}
}
},
"workers": {
"total": 5.529433932102165,
"count": 232160,
"self": 0.0,
"children": {
"worker_root": {
"total": 4644.073292254194,
"count": 232160,
"is_parallel": true,
"self": 2626.6514428440896,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001033880000022691,
"count": 1,
"is_parallel": true,
"self": 0.0002358379999805038,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007980420000421873,
"count": 2,
"is_parallel": true,
"self": 0.0007980420000421873
}
}
},
"UnityEnvironment.step": {
"total": 0.039673760000141556,
"count": 1,
"is_parallel": true,
"self": 0.000503632000345533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00027823599998555437,
"count": 1,
"is_parallel": true,
"self": 0.00027823599998555437
},
"communicator.exchange": {
"total": 0.03787090699984219,
"count": 1,
"is_parallel": true,
"self": 0.03787090699984219
},
"steps_from_proto": {
"total": 0.0010209849999682774,
"count": 1,
"is_parallel": true,
"self": 0.0002445210000132647,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007764639999550127,
"count": 2,
"is_parallel": true,
"self": 0.0007764639999550127
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2017.421849410104,
"count": 232159,
"is_parallel": true,
"self": 63.32945458706695,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 96.48975679992895,
"count": 232159,
"is_parallel": true,
"self": 96.48975679992895
},
"communicator.exchange": {
"total": 1715.3495832570293,
"count": 232159,
"is_parallel": true,
"self": 1715.3495832570293
},
"steps_from_proto": {
"total": 142.25305476607878,
"count": 232159,
"is_parallel": true,
"self": 45.46815575006667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 96.7848990160121,
"count": 464318,
"is_parallel": true,
"self": 96.7848990160121
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1588.7142696399674,
"count": 232160,
"self": 13.09756955685316,
"children": {
"process_trajectory": {
"total": 248.85683837811234,
"count": 232160,
"self": 247.58851562711243,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2683227509999142,
"count": 10,
"self": 1.2683227509999142
}
}
},
"_update_policy": {
"total": 1326.7598617050019,
"count": 97,
"self": 326.26172345603027,
"children": {
"TorchPPOOptimizer.update": {
"total": 1000.4981382489716,
"count": 2910,
"self": 1000.4981382489716
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1309994079056196e-06,
"count": 1,
"self": 1.1309994079056196e-06
},
"TrainerController._save_models": {
"total": 0.11978900200028875,
"count": 1,
"self": 0.0038872950008226326,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11590170699946611,
"count": 1,
"self": 0.11590170699946611
}
}
}
}
}
}
}