RL_course_unit3 / run_logs /timers.json
hanq0212's picture
First Pyramids
d07d24a
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.8746827244758606,
"min": 0.8316496014595032,
"max": 1.4774277210235596,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 26310.45703125,
"min": 24962.794921875,
"max": 44819.24609375,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479930.0,
"min": 29994.0,
"max": 479930.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479930.0,
"min": 29994.0,
"max": 479930.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.01624610833823681,
"min": -0.3146287798881531,
"max": -0.01624610833823681,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -3.9153122901916504,
"min": -74.88165283203125,
"max": -3.9153122901916504,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03006104752421379,
"min": 0.025296669453382492,
"max": 0.2601739764213562,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.2447123527526855,
"min": 6.096497535705566,
"max": 62.44175338745117,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06988094395313689,
"min": 0.0659174787230473,
"max": 0.07725611824087518,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9783332153439164,
"min": 0.5407928276861262,
"max": 0.989881582105619,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0024227697882574337,
"min": 0.0005141955552607118,
"max": 0.006950746215356144,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.03391877703560407,
"min": 0.006684542218389254,
"max": 0.04865522350749301,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.1455621419585715e-05,
"min": 2.1455621419585715e-05,
"max": 0.00029047320317559996,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0003003786998742,
"min": 0.0003003786998742,
"max": 0.0028383003539,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10715184285714287,
"min": 0.10715184285714287,
"max": 0.19682440000000004,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5001258000000002,
"min": 1.3777708000000002,
"max": 2.2461000000000007,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007244691014285715,
"min": 0.0007244691014285715,
"max": 0.00968275756,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.010142567420000002,
"min": 0.010142567420000002,
"max": 0.09464539000000001,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.02698243223130703,
"min": 0.02698243223130703,
"max": 0.4409971237182617,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3777540624141693,
"min": 0.3777540624141693,
"max": 3.086979866027832,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 978.625,
"min": 922.25,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31316.0,
"min": 16665.0,
"max": 31968.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.7205355321207354,
"min": -0.9999750521965325,
"max": -0.4852625490166247,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -22.336601495742798,
"min": -31.99920167028904,
"max": -14.681000873446465,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.7205355321207354,
"min": -0.9999750521965325,
"max": -0.4852625490166247,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -22.336601495742798,
"min": -31.99920167028904,
"max": -14.681000873446465,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.2734389911976553,
"min": 0.2731584718276281,
"max": 7.615341357010252,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.476608727127314,
"min": 8.476608727127314,
"max": 129.4608030691743,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1671634053",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1671635008"
},
"total": 954.633990965,
"count": 1,
"self": 0.44929530699982934,
"children": {
"run_training.setup": {
"total": 0.10899317500002326,
"count": 1,
"self": 0.10899317500002326
},
"TrainerController.start_learning": {
"total": 954.0757024830001,
"count": 1,
"self": 0.5750407550365253,
"children": {
"TrainerController._reset_env": {
"total": 7.471981321000044,
"count": 1,
"self": 7.471981321000044
},
"TrainerController.advance": {
"total": 945.8855820089636,
"count": 31570,
"self": 0.6122840609965579,
"children": {
"env_step": {
"total": 616.4525375539938,
"count": 31570,
"self": 565.1843603820217,
"children": {
"SubprocessEnvManager._take_step": {
"total": 50.900976367987255,
"count": 31570,
"self": 2.137308965981333,
"children": {
"TorchPolicy.evaluate": {
"total": 48.76366740200592,
"count": 31322,
"self": 16.524531247980235,
"children": {
"TorchPolicy.sample_actions": {
"total": 32.23913615402569,
"count": 31322,
"self": 32.23913615402569
}
}
}
}
},
"workers": {
"total": 0.36720080398481514,
"count": 31570,
"self": 0.0,
"children": {
"worker_root": {
"total": 951.8780449189918,
"count": 31570,
"is_parallel": true,
"self": 434.6375714459758,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053216969999994035,
"count": 1,
"is_parallel": true,
"self": 0.003131400000143003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021902969998564004,
"count": 8,
"is_parallel": true,
"self": 0.0021902969998564004
}
}
},
"UnityEnvironment.step": {
"total": 0.0462234089999356,
"count": 1,
"is_parallel": true,
"self": 0.0005085049998569957,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004282659999716998,
"count": 1,
"is_parallel": true,
"self": 0.0004282659999716998
},
"communicator.exchange": {
"total": 0.043723924000005354,
"count": 1,
"is_parallel": true,
"self": 0.043723924000005354
},
"steps_from_proto": {
"total": 0.0015627140001015505,
"count": 1,
"is_parallel": true,
"self": 0.0004005979999419651,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011621160001595854,
"count": 8,
"is_parallel": true,
"self": 0.0011621160001595854
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 517.240473473016,
"count": 31569,
"is_parallel": true,
"self": 14.040678984011606,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.94351097598792,
"count": 31569,
"is_parallel": true,
"self": 11.94351097598792
},
"communicator.exchange": {
"total": 443.59502019800686,
"count": 31569,
"is_parallel": true,
"self": 443.59502019800686
},
"steps_from_proto": {
"total": 47.66126331500959,
"count": 31569,
"is_parallel": true,
"self": 11.015088757984927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.646174557024665,
"count": 252552,
"is_parallel": true,
"self": 36.646174557024665
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 328.8207603939733,
"count": 31570,
"self": 0.9847824919723962,
"children": {
"process_trajectory": {
"total": 72.8055588370014,
"count": 31570,
"self": 72.65179650700134,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15376233000006323,
"count": 1,
"self": 0.15376233000006323
}
}
},
"_update_policy": {
"total": 255.03041906499948,
"count": 214,
"self": 99.98832861199003,
"children": {
"TorchPPOOptimizer.update": {
"total": 155.04209045300945,
"count": 11427,
"self": 155.04209045300945
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3889998626837041e-06,
"count": 1,
"self": 1.3889998626837041e-06
},
"TrainerController._save_models": {
"total": 0.14309700900003008,
"count": 1,
"self": 0.0018280400001913222,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14126896899983876,
"count": 1,
"self": 0.14126896899983876
}
}
}
}
}
}
}