ppo-Huggy / run_logs /timers.json
hqbui's picture
Huggy
509b005
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4025565385818481,
"min": 1.4025565385818481,
"max": 1.427955150604248,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70833.3125,
"min": 68118.875,
"max": 77672.71875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.10296411856474,
"min": 77.10296411856474,
"max": 381.05384615384617,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49423.0,
"min": 48945.0,
"max": 50272.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999950.0,
"min": 49783.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999950.0,
"min": 49783.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.442261219024658,
"min": 0.07322973757982254,
"max": 2.488520860671997,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1565.4893798828125,
"min": 9.666325569152832,
"max": 1565.4893798828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8555024902273822,
"min": 1.823510523998376,
"max": 3.9744658896583833,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2471.377096235752,
"min": 240.70338916778564,
"max": 2471.377096235752,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8555024902273822,
"min": 1.823510523998376,
"max": 3.9744658896583833,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2471.377096235752,
"min": 240.70338916778564,
"max": 2471.377096235752,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019001007877846456,
"min": 0.0129781767129316,
"max": 0.0204808633462057,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05700302363353937,
"min": 0.0259563534258632,
"max": 0.0614425900386171,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.061621261636416125,
"min": 0.022491332702338693,
"max": 0.0680585902184248,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18486378490924837,
"min": 0.046957290607194106,
"max": 0.20417577065527437,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.478198840633327e-06,
"min": 3.478198840633327e-06,
"max": 0.0002952705765764749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0434596521899981e-05,
"min": 1.0434596521899981e-05,
"max": 0.0008438619187126999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115936666666663,
"min": 0.10115936666666663,
"max": 0.198423525,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347809999999986,
"min": 0.20744780000000004,
"max": 0.5812873000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.785239666666661e-05,
"min": 6.785239666666661e-05,
"max": 0.004921333897499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020355718999999983,
"min": 0.00020355718999999983,
"max": 0.01406623627,
"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": "1697030238",
"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": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697032938"
},
"total": 2700.319205566,
"count": 1,
"self": 0.7344879070005845,
"children": {
"run_training.setup": {
"total": 0.04873237500009964,
"count": 1,
"self": 0.04873237500009964
},
"TrainerController.start_learning": {
"total": 2699.5359852839997,
"count": 1,
"self": 5.4634523760396405,
"children": {
"TrainerController._reset_env": {
"total": 8.274014314000055,
"count": 1,
"self": 8.274014314000055
},
"TrainerController.advance": {
"total": 2685.62238736596,
"count": 232403,
"self": 5.263206293062467,
"children": {
"env_step": {
"total": 2128.580630400958,
"count": 232403,
"self": 1763.711637802045,
"children": {
"SubprocessEnvManager._take_step": {
"total": 361.4172773919804,
"count": 232403,
"self": 18.640476964033155,
"children": {
"TorchPolicy.evaluate": {
"total": 342.77680042794725,
"count": 222947,
"self": 342.77680042794725
}
}
},
"workers": {
"total": 3.4517152069324766,
"count": 232403,
"self": 0.0,
"children": {
"worker_root": {
"total": 2691.0949459409103,
"count": 232403,
"is_parallel": true,
"self": 1257.6518243639625,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012880909999921641,
"count": 1,
"is_parallel": true,
"self": 0.0003136980000135736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009743929999785905,
"count": 2,
"is_parallel": true,
"self": 0.0009743929999785905
}
}
},
"UnityEnvironment.step": {
"total": 0.029826909000007618,
"count": 1,
"is_parallel": true,
"self": 0.0003110719999313005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026717600007941655,
"count": 1,
"is_parallel": true,
"self": 0.00026717600007941655
},
"communicator.exchange": {
"total": 0.02847144899999421,
"count": 1,
"is_parallel": true,
"self": 0.02847144899999421
},
"steps_from_proto": {
"total": 0.0007772120000026916,
"count": 1,
"is_parallel": true,
"self": 0.00021485799993570254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005623540000669891,
"count": 2,
"is_parallel": true,
"self": 0.0005623540000669891
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1433.4431215769478,
"count": 232402,
"is_parallel": true,
"self": 45.170449713088146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.61473856887937,
"count": 232402,
"is_parallel": true,
"self": 91.61473856887937
},
"communicator.exchange": {
"total": 1194.9298907249527,
"count": 232402,
"is_parallel": true,
"self": 1194.9298907249527
},
"steps_from_proto": {
"total": 101.72804257002758,
"count": 232402,
"is_parallel": true,
"self": 35.408830776162176,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.3192117938654,
"count": 464804,
"is_parallel": true,
"self": 66.3192117938654
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 551.7785506719395,
"count": 232403,
"self": 7.617686218859262,
"children": {
"process_trajectory": {
"total": 163.88970237408103,
"count": 232403,
"self": 162.37979133208182,
"children": {
"RLTrainer._checkpoint": {
"total": 1.509911041999203,
"count": 10,
"self": 1.509911041999203
}
}
},
"_update_policy": {
"total": 380.27116207899917,
"count": 97,
"self": 313.08846684300033,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.18269523599884,
"count": 2910,
"self": 67.18269523599884
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.8440000530972611e-06,
"count": 1,
"self": 1.8440000530972611e-06
},
"TrainerController._save_models": {
"total": 0.17612938399997802,
"count": 1,
"self": 0.0027597220000643574,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17336966199991366,
"count": 1,
"self": 0.17336966199991366
}
}
}
}
}
}
}