ppo-Huggy / run_logs /timers.json
shadowlilac's picture
Huggy
52ee488 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407757043838501,
"min": 1.407757043838501,
"max": 1.4287841320037842,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69883.875,
"min": 66948.0,
"max": 79306.34375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.90395480225989,
"min": 83.89115646258503,
"max": 378.82706766917295,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49332.0,
"min": 48930.0,
"max": 50384.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999930.0,
"min": 49970.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999930.0,
"min": 49970.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4866783618927,
"min": 0.13814617693424225,
"max": 2.4866783618927,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1320.4261474609375,
"min": 18.23529624938965,
"max": 1382.701171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.981941148610663,
"min": 1.9449494882966534,
"max": 3.981941148610663,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2114.410749912262,
"min": 256.73333245515823,
"max": 2195.2585330605507,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.981941148610663,
"min": 1.9449494882966534,
"max": 3.981941148610663,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2114.410749912262,
"min": 256.73333245515823,
"max": 2195.2585330605507,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014597478678559936,
"min": 0.014371060062452062,
"max": 0.020794679591199385,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04379243603567981,
"min": 0.028742120124904125,
"max": 0.06131290492485277,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05265085912413068,
"min": 0.022880566554764906,
"max": 0.05654425273338953,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15795257737239204,
"min": 0.04576113310952981,
"max": 0.1696327582001686,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.61544879488334e-06,
"min": 3.61544879488334e-06,
"max": 0.00029535135154954995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.084634638465002e-05,
"min": 1.084634638465002e-05,
"max": 0.0008441560686146498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120511666666669,
"min": 0.10120511666666669,
"max": 0.19845045000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30361535000000006,
"min": 0.20755150000000003,
"max": 0.5813853499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.013532166666676e-05,
"min": 7.013532166666676e-05,
"max": 0.004922677455,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021040596500000028,
"min": 0.00021040596500000028,
"max": 0.014071128964999999,
"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": "1734383881",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734385927"
},
"total": 2046.454799258,
"count": 1,
"self": 0.32128420200024266,
"children": {
"run_training.setup": {
"total": 0.062141500000052474,
"count": 1,
"self": 0.062141500000052474
},
"TrainerController.start_learning": {
"total": 2046.0713735559998,
"count": 1,
"self": 4.090752027987492,
"children": {
"TrainerController._reset_env": {
"total": 4.9837751380000554,
"count": 1,
"self": 4.9837751380000554
},
"TrainerController.advance": {
"total": 2036.8864636230123,
"count": 232292,
"self": 4.134234797008958,
"children": {
"env_step": {
"total": 1584.714367297076,
"count": 232292,
"self": 1200.0242886161398,
"children": {
"SubprocessEnvManager._take_step": {
"total": 382.09059622797236,
"count": 232292,
"self": 14.908376159889826,
"children": {
"TorchPolicy.evaluate": {
"total": 367.18222006808253,
"count": 222929,
"self": 367.18222006808253
}
}
},
"workers": {
"total": 2.599482452963912,
"count": 232292,
"self": 0.0,
"children": {
"worker_root": {
"total": 2039.0981664649116,
"count": 232292,
"is_parallel": true,
"self": 1073.3310712660518,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008374330000151531,
"count": 1,
"is_parallel": true,
"self": 0.0002747339999586984,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005626990000564547,
"count": 2,
"is_parallel": true,
"self": 0.0005626990000564547
}
}
},
"UnityEnvironment.step": {
"total": 0.022402259999921625,
"count": 1,
"is_parallel": true,
"self": 0.00028745399993113097,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020249700003205362,
"count": 1,
"is_parallel": true,
"self": 0.00020249700003205362
},
"communicator.exchange": {
"total": 0.02141689799998403,
"count": 1,
"is_parallel": true,
"self": 0.02141689799998403
},
"steps_from_proto": {
"total": 0.0004954109999744105,
"count": 1,
"is_parallel": true,
"self": 0.00015018199997030024,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003452290000041103,
"count": 2,
"is_parallel": true,
"self": 0.0003452290000041103
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 965.7670951988597,
"count": 232291,
"is_parallel": true,
"self": 26.32510542106172,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 49.016983640818125,
"count": 232291,
"is_parallel": true,
"self": 49.016983640818125
},
"communicator.exchange": {
"total": 831.0468908000178,
"count": 232291,
"is_parallel": true,
"self": 831.0468908000178
},
"steps_from_proto": {
"total": 59.37811533696208,
"count": 232291,
"is_parallel": true,
"self": 22.875996290912212,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.50211904604987,
"count": 464582,
"is_parallel": true,
"self": 36.50211904604987
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 448.03786152892746,
"count": 232292,
"self": 6.164612207939285,
"children": {
"process_trajectory": {
"total": 151.39307144998645,
"count": 232292,
"self": 149.9499945239861,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4430769260003444,
"count": 10,
"self": 1.4430769260003444
}
}
},
"_update_policy": {
"total": 290.48017787100173,
"count": 97,
"self": 237.3609907939965,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.11918707700522,
"count": 2910,
"self": 53.11918707700522
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1229999472561758e-06,
"count": 1,
"self": 1.1229999472561758e-06
},
"TrainerController._save_models": {
"total": 0.11038164399997186,
"count": 1,
"self": 0.0023098530000424944,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10807179099992936,
"count": 1,
"self": 0.10807179099992936
}
}
}
}
}
}
}