ppo-Huggy / run_logs /timers.json
electricwapiti's picture
Huggy
95ec5a2 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4050287008285522,
"min": 1.4050287008285522,
"max": 1.430539846420288,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70287.96875,
"min": 67664.15625,
"max": 78178.8671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 106.9438444924406,
"min": 94.07414448669202,
"max": 382.21374045801525,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49515.0,
"min": 48939.0,
"max": 50431.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49848.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49848.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3400397300720215,
"min": 0.2190191149711609,
"max": 2.40055775642395,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1083.4383544921875,
"min": 28.472484588623047,
"max": 1246.8447265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6053624191757927,
"min": 1.7443212610024672,
"max": 3.7942615856356143,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1669.282800078392,
"min": 226.76176393032074,
"max": 1948.706189751625,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6053624191757927,
"min": 1.7443212610024672,
"max": 3.7942615856356143,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1669.282800078392,
"min": 226.76176393032074,
"max": 1948.706189751625,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01701610609452473,
"min": 0.01378042152840256,
"max": 0.02040727120814457,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03403221218904946,
"min": 0.02756084305680512,
"max": 0.059460591175593436,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04727988677720229,
"min": 0.021406262119611105,
"max": 0.06582114938646555,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09455977355440458,
"min": 0.04281252423922221,
"max": 0.19334582475324472,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.324148558649991e-06,
"min": 4.324148558649991e-06,
"max": 0.0002953596765467749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.648297117299982e-06,
"min": 8.648297117299982e-06,
"max": 0.0008440215186595,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10144135,
"min": 0.10144135,
"max": 0.19845322499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2028827,
"min": 0.2028827,
"max": 0.5813405000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.192336499999982e-05,
"min": 8.192336499999982e-05,
"max": 0.004922815927500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016384672999999965,
"min": 0.00016384672999999965,
"max": 0.01406889095,
"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": "1723568728",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723573462"
},
"total": 4734.483364828,
"count": 1,
"self": 0.7050999410002987,
"children": {
"run_training.setup": {
"total": 0.0869941439999593,
"count": 1,
"self": 0.0869941439999593
},
"TrainerController.start_learning": {
"total": 4733.691270743,
"count": 1,
"self": 8.370479084893304,
"children": {
"TrainerController._reset_env": {
"total": 4.212334582999915,
"count": 1,
"self": 4.212334582999915
},
"TrainerController.advance": {
"total": 4720.993979737108,
"count": 230984,
"self": 8.414662665069955,
"children": {
"env_step": {
"total": 2996.810423995998,
"count": 230984,
"self": 2490.674851403223,
"children": {
"SubprocessEnvManager._take_step": {
"total": 500.4412517607486,
"count": 230984,
"self": 32.491186096683805,
"children": {
"TorchPolicy.evaluate": {
"total": 467.9500656640648,
"count": 222901,
"self": 467.9500656640648
}
}
},
"workers": {
"total": 5.694320832026506,
"count": 230984,
"self": 0.0,
"children": {
"worker_root": {
"total": 4721.000487049079,
"count": 230984,
"is_parallel": true,
"self": 2741.9241543711614,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0015007549999381808,
"count": 1,
"is_parallel": true,
"self": 0.00041035200001715566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010904029999210252,
"count": 2,
"is_parallel": true,
"self": 0.0010904029999210252
}
}
},
"UnityEnvironment.step": {
"total": 0.03850069000009171,
"count": 1,
"is_parallel": true,
"self": 0.0005105889999867941,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032788800001526397,
"count": 1,
"is_parallel": true,
"self": 0.00032788800001526397
},
"communicator.exchange": {
"total": 0.036700111000072866,
"count": 1,
"is_parallel": true,
"self": 0.036700111000072866
},
"steps_from_proto": {
"total": 0.0009621020000167846,
"count": 1,
"is_parallel": true,
"self": 0.00023283300004095508,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007292689999758295,
"count": 2,
"is_parallel": true,
"self": 0.0007292689999758295
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1979.076332677918,
"count": 230983,
"is_parallel": true,
"self": 62.20939706493073,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 110.84979785008898,
"count": 230983,
"is_parallel": true,
"self": 110.84979785008898
},
"communicator.exchange": {
"total": 1665.7880752618955,
"count": 230983,
"is_parallel": true,
"self": 1665.7880752618955
},
"steps_from_proto": {
"total": 140.22906250100277,
"count": 230983,
"is_parallel": true,
"self": 45.094598677983186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 95.13446382301959,
"count": 461966,
"is_parallel": true,
"self": 95.13446382301959
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1715.76889307604,
"count": 230984,
"self": 13.339217745159203,
"children": {
"process_trajectory": {
"total": 251.8284772158795,
"count": 230984,
"self": 250.36919257787963,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4592846379998718,
"count": 10,
"self": 1.4592846379998718
}
}
},
"_update_policy": {
"total": 1450.6011981150014,
"count": 96,
"self": 355.3978419980026,
"children": {
"TorchPPOOptimizer.update": {
"total": 1095.2033561169987,
"count": 2880,
"self": 1095.2033561169987
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0399999155197293e-06,
"count": 1,
"self": 1.0399999155197293e-06
},
"TrainerController._save_models": {
"total": 0.11447629799931747,
"count": 1,
"self": 0.003322314999422815,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11115398299989465,
"count": 1,
"self": 0.11115398299989465
}
}
}
}
}
}
}