ppo-Huggy / run_logs /timers.json
mittelmandaniel's picture
Huggy
98476e1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403053641319275,
"min": 1.4030057191848755,
"max": 1.4277164936065674,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71700.25,
"min": 67586.4140625,
"max": 78476.5703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.119926199262,
"min": 91.48243992606285,
"max": 403.39516129032256,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49929.0,
"min": 48847.0,
"max": 50233.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999763.0,
"min": 49982.0,
"max": 1999763.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999763.0,
"min": 49982.0,
"max": 1999763.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.333191394805908,
"min": 0.09590285271406174,
"max": 2.396455764770508,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1264.5897216796875,
"min": 11.796051025390625,
"max": 1264.5897216796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6295097324021186,
"min": 1.8314253708453683,
"max": 3.91443254532793,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1967.1942749619484,
"min": 225.2653206139803,
"max": 1990.3986637592316,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6295097324021186,
"min": 1.8314253708453683,
"max": 3.91443254532793,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1967.1942749619484,
"min": 225.2653206139803,
"max": 1990.3986637592316,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01691116594496028,
"min": 0.012249380072019752,
"max": 0.0201684127105788,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03382233188992056,
"min": 0.024498760144039504,
"max": 0.05622514819988282,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05634168094644944,
"min": 0.02133862841874361,
"max": 0.05634168094644944,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11268336189289888,
"min": 0.04267725683748722,
"max": 0.15422722299893699,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.458998513700004e-06,
"min": 4.458998513700004e-06,
"max": 0.00029535825154724995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.917997027400008e-06,
"min": 8.917997027400008e-06,
"max": 0.0008439100686966501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1014863,
"min": 0.1014863,
"max": 0.19845274999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2029726,
"min": 0.2029726,
"max": 0.58130335,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.416637000000007e-05,
"min": 8.416637000000007e-05,
"max": 0.004922792225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016833274000000015,
"min": 0.00016833274000000015,
"max": 0.014067037164999999,
"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": "1698722662",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698725052"
},
"total": 2390.23876537,
"count": 1,
"self": 0.735451670999737,
"children": {
"run_training.setup": {
"total": 0.04617890100007571,
"count": 1,
"self": 0.04617890100007571
},
"TrainerController.start_learning": {
"total": 2389.457134798,
"count": 1,
"self": 4.287838892033051,
"children": {
"TrainerController._reset_env": {
"total": 8.669015264999985,
"count": 1,
"self": 8.669015264999985
},
"TrainerController.advance": {
"total": 2376.3435897009676,
"count": 231284,
"self": 4.578674914069779,
"children": {
"env_step": {
"total": 1895.2954411898652,
"count": 231284,
"self": 1559.5396172069263,
"children": {
"SubprocessEnvManager._take_step": {
"total": 333.0265736569976,
"count": 231284,
"self": 17.087408520071108,
"children": {
"TorchPolicy.evaluate": {
"total": 315.9391651369265,
"count": 222938,
"self": 315.9391651369265
}
}
},
"workers": {
"total": 2.7292503259413934,
"count": 231284,
"self": 0.0,
"children": {
"worker_root": {
"total": 2381.8810948349674,
"count": 231284,
"is_parallel": true,
"self": 1110.4529197579782,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008798400000387119,
"count": 1,
"is_parallel": true,
"self": 0.00023778299998866714,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006420570000500447,
"count": 2,
"is_parallel": true,
"self": 0.0006420570000500447
}
}
},
"UnityEnvironment.step": {
"total": 0.02876559300000281,
"count": 1,
"is_parallel": true,
"self": 0.00030640099998890946,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020105900000544352,
"count": 1,
"is_parallel": true,
"self": 0.00020105900000544352
},
"communicator.exchange": {
"total": 0.027586754000026303,
"count": 1,
"is_parallel": true,
"self": 0.027586754000026303
},
"steps_from_proto": {
"total": 0.0006713789999821529,
"count": 1,
"is_parallel": true,
"self": 0.00019083199981650978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004805470001656431,
"count": 2,
"is_parallel": true,
"self": 0.0004805470001656431
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1271.4281750769892,
"count": 231283,
"is_parallel": true,
"self": 40.58142133296883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.33131063001929,
"count": 231283,
"is_parallel": true,
"self": 82.33131063001929
},
"communicator.exchange": {
"total": 1058.4049150470607,
"count": 231283,
"is_parallel": true,
"self": 1058.4049150470607
},
"steps_from_proto": {
"total": 90.11052806694033,
"count": 231283,
"is_parallel": true,
"self": 31.699135394707355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.41139267223298,
"count": 462566,
"is_parallel": true,
"self": 58.41139267223298
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 476.4694735970328,
"count": 231284,
"self": 6.4835377000446215,
"children": {
"process_trajectory": {
"total": 142.40194672298583,
"count": 231284,
"self": 141.25818319298503,
"children": {
"RLTrainer._checkpoint": {
"total": 1.143763530000797,
"count": 10,
"self": 1.143763530000797
}
}
},
"_update_policy": {
"total": 327.58398917400234,
"count": 96,
"self": 266.47955338500685,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.10443578899549,
"count": 2880,
"self": 61.10443578899549
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3139997463440523e-06,
"count": 1,
"self": 1.3139997463440523e-06
},
"TrainerController._save_models": {
"total": 0.15668962599966108,
"count": 1,
"self": 0.0035745999998653133,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15311502599979576,
"count": 1,
"self": 0.15311502599979576
}
}
}
}
}
}
}