ppo-Huggy / run_logs /timers.json
jguevara's picture
Huggy
8d21b2d
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407745599746704,
"min": 1.407745599746704,
"max": 1.4275004863739014,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69359.625,
"min": 69078.4765625,
"max": 76948.328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.44273504273504,
"min": 72.88643067846607,
"max": 424.2542372881356,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48814.0,
"min": 48814.0,
"max": 50062.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999910.0,
"min": 49504.0,
"max": 1999910.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999910.0,
"min": 49504.0,
"max": 1999910.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.412031650543213,
"min": 0.07540160417556763,
"max": 2.5042238235473633,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1411.03857421875,
"min": 8.821988105773926,
"max": 1667.483154296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6116617370874455,
"min": 1.716623819918714,
"max": 4.103123759380495,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2112.8221161961555,
"min": 200.84498693048954,
"max": 2631.090379834175,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6116617370874455,
"min": 1.716623819918714,
"max": 4.103123759380495,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2112.8221161961555,
"min": 200.84498693048954,
"max": 2631.090379834175,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015825438973600586,
"min": 0.014721619241916213,
"max": 0.020891248538949487,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04747631692080176,
"min": 0.030387665629192876,
"max": 0.05807545150552566,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05835038349032403,
"min": 0.022026336317261058,
"max": 0.06200357209891081,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17505115047097208,
"min": 0.044052672634522116,
"max": 0.17732554823160174,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7179487607166664e-06,
"min": 3.7179487607166664e-06,
"max": 0.00029530567656477495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.115384628215e-05,
"min": 1.115384628215e-05,
"max": 0.0008440660686446498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123928333333333,
"min": 0.10123928333333333,
"max": 0.19843522500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30371785,
"min": 0.20761525000000003,
"max": 0.5813553499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.184023833333335e-05,
"min": 7.184023833333335e-05,
"max": 0.004921917727499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021552071500000004,
"min": 0.00021552071500000004,
"max": 0.014069631965,
"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": "1700612494",
"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": "1700614984"
},
"total": 2490.198745111,
"count": 1,
"self": 0.43126848500014603,
"children": {
"run_training.setup": {
"total": 0.08030453599997145,
"count": 1,
"self": 0.08030453599997145
},
"TrainerController.start_learning": {
"total": 2489.68717209,
"count": 1,
"self": 4.510053357993456,
"children": {
"TrainerController._reset_env": {
"total": 10.403957891000005,
"count": 1,
"self": 10.403957891000005
},
"TrainerController.advance": {
"total": 2474.6635603040063,
"count": 233183,
"self": 4.6950223620337965,
"children": {
"env_step": {
"total": 1952.175947540974,
"count": 233183,
"self": 1611.4168246549634,
"children": {
"SubprocessEnvManager._take_step": {
"total": 337.89371241797903,
"count": 233183,
"self": 17.335104121050108,
"children": {
"TorchPolicy.evaluate": {
"total": 320.5586082969289,
"count": 222994,
"self": 320.5586082969289
}
}
},
"workers": {
"total": 2.8654104680315413,
"count": 233183,
"self": 0.0,
"children": {
"worker_root": {
"total": 2482.146163968025,
"count": 233183,
"is_parallel": true,
"self": 1169.1277675059973,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000907107999978507,
"count": 1,
"is_parallel": true,
"self": 0.0002643309999257326,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006427770000527744,
"count": 2,
"is_parallel": true,
"self": 0.0006427770000527744
}
}
},
"UnityEnvironment.step": {
"total": 0.04890852200003337,
"count": 1,
"is_parallel": true,
"self": 0.00028592000001026463,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018984300004376564,
"count": 1,
"is_parallel": true,
"self": 0.00018984300004376564
},
"communicator.exchange": {
"total": 0.04773700999999164,
"count": 1,
"is_parallel": true,
"self": 0.04773700999999164
},
"steps_from_proto": {
"total": 0.0006957489999876998,
"count": 1,
"is_parallel": true,
"self": 0.00020646800010126753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004892809998864323,
"count": 2,
"is_parallel": true,
"self": 0.0004892809998864323
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1313.0183964620278,
"count": 233182,
"is_parallel": true,
"self": 41.12190980804189,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.54433152096215,
"count": 233182,
"is_parallel": true,
"self": 83.54433152096215
},
"communicator.exchange": {
"total": 1097.5917861289054,
"count": 233182,
"is_parallel": true,
"self": 1097.5917861289054
},
"steps_from_proto": {
"total": 90.76036900411839,
"count": 233182,
"is_parallel": true,
"self": 32.00392773392082,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.75644127019757,
"count": 466364,
"is_parallel": true,
"self": 58.75644127019757
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 517.7925904009983,
"count": 233183,
"self": 6.7545993959527095,
"children": {
"process_trajectory": {
"total": 164.46751471804384,
"count": 233183,
"self": 163.26289465404375,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2046200640000961,
"count": 10,
"self": 1.2046200640000961
}
}
},
"_update_policy": {
"total": 346.5704762870017,
"count": 97,
"self": 283.4465043159927,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.12397197100904,
"count": 2910,
"self": 63.12397197100904
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.47299988384475e-06,
"count": 1,
"self": 1.47299988384475e-06
},
"TrainerController._save_models": {
"total": 0.10959906400012187,
"count": 1,
"self": 0.001946295000379905,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10765276899974197,
"count": 1,
"self": 0.10765276899974197
}
}
}
}
}
}
}