ppo-Pyramids / run_logs /timers.json
alberto-mate's picture
First Push
095886a
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.4917479753494263,
"min": 1.4917479753494263,
"max": 1.4917479753494263,
"count": 1
},
"Pyramids.Policy.Entropy.sum": {
"value": 45253.66796875,
"min": 45253.66796875,
"max": 45253.66796875,
"count": 1
},
"Pyramids.Step.mean": {
"value": 29883.0,
"min": 29883.0,
"max": 29883.0,
"count": 1
},
"Pyramids.Step.sum": {
"value": 29883.0,
"min": 29883.0,
"max": 29883.0,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.2075425535440445,
"min": -0.2075425535440445,
"max": -0.2075425535440445,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -49.187583923339844,
"min": -49.187583923339844,
"max": -49.187583923339844,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.15217599272727966,
"min": 0.15217599272727966,
"max": 0.15217599272727966,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 36.065711975097656,
"min": 36.065711975097656,
"max": 36.065711975097656,
"count": 1
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06762662689194461,
"min": 0.06762662689194461,
"max": 0.06762662689194461,
"count": 1
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.4733863882436123,
"min": 0.4733863882436123,
"max": 0.4733863882436123,
"count": 1
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005895055853062213,
"min": 0.005895055853062213,
"max": 0.005895055853062213,
"count": 1
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.04126539097143549,
"min": 0.04126539097143549,
"max": 0.04126539097143549,
"count": 1
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00013835433959619045,
"min": 0.00013835433959619045,
"max": 0.00013835433959619045,
"count": 1
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0009684803771733332,
"min": 0.0009684803771733332,
"max": 0.0009684803771733332,
"count": 1
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1461180952380953,
"min": 0.1461180952380953,
"max": 0.1461180952380953,
"count": 1
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.022826666666667,
"min": 1.022826666666667,
"max": 1.022826666666667,
"count": 1
},
"Pyramids.Policy.Beta.mean": {
"value": 0.004617197714285715,
"min": 0.004617197714285715,
"max": 0.004617197714285715,
"count": 1
},
"Pyramids.Policy.Beta.sum": {
"value": 0.032320384,
"min": 0.032320384,
"max": 0.032320384,
"count": 1
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.3930913805961609,
"min": 0.3930913805961609,
"max": 0.3930913805961609,
"count": 1
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 2.7516396045684814,
"min": 2.7516396045684814,
"max": 2.7516396045684814,
"count": 1
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 988.8235294117648,
"min": 988.8235294117648,
"max": 988.8235294117648,
"count": 1
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 16810.0,
"min": 16810.0,
"max": 16810.0,
"count": 1
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.8721176964395186,
"min": -0.8721176964395186,
"max": -0.8721176964395186,
"count": 1
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -14.826000839471817,
"min": -14.826000839471817,
"max": -14.826000839471817,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.8721176964395186,
"min": -0.8721176964395186,
"max": -0.8721176964395186,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -14.826000839471817,
"min": -14.826000839471817,
"max": -14.826000839471817,
"count": 1
},
"Pyramids.Policy.RndReward.mean": {
"value": 8.085533689926653,
"min": 8.085533689926653,
"max": 8.085533689926653,
"count": 1
},
"Pyramids.Policy.RndReward.sum": {
"value": 137.4540727287531,
"min": 137.4540727287531,
"max": 137.4540727287531,
"count": 1
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677758514",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --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": "1.22.4",
"end_time_seconds": "1677758577"
},
"total": 63.22450938199995,
"count": 1,
"self": 0.4769018969999479,
"children": {
"run_training.setup": {
"total": 0.19655202000001282,
"count": 1,
"self": 0.19655202000001282
},
"TrainerController.start_learning": {
"total": 62.55105546499999,
"count": 1,
"self": 0.041282118002300194,
"children": {
"TrainerController._reset_env": {
"total": 6.368508062000046,
"count": 1,
"self": 6.368508062000046
},
"TrainerController.advance": {
"total": 56.04195763099756,
"count": 1897,
"self": 0.0471080369959509,
"children": {
"env_step": {
"total": 35.29898593599978,
"count": 1897,
"self": 31.488136000007103,
"children": {
"SubprocessEnvManager._take_step": {
"total": 3.7821996399964064,
"count": 1897,
"self": 0.14884624899866594,
"children": {
"TorchPolicy.evaluate": {
"total": 3.6333533909977405,
"count": 1896,
"self": 1.1787705999954596,
"children": {
"TorchPolicy.sample_actions": {
"total": 2.454582791002281,
"count": 1896,
"self": 2.454582791002281
}
}
}
}
},
"workers": {
"total": 0.02865029599627178,
"count": 1897,
"self": 0.0,
"children": {
"worker_root": {
"total": 62.1330622110014,
"count": 1897,
"is_parallel": true,
"self": 34.1219196680006,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019440249999433945,
"count": 1,
"is_parallel": true,
"self": 0.0007241519998615331,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012198730000818614,
"count": 8,
"is_parallel": true,
"self": 0.0012198730000818614
}
}
},
"UnityEnvironment.step": {
"total": 0.05129701800001385,
"count": 1,
"is_parallel": true,
"self": 0.0005364970000982794,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005124949999526507,
"count": 1,
"is_parallel": true,
"self": 0.0005124949999526507
},
"communicator.exchange": {
"total": 0.04857179199996153,
"count": 1,
"is_parallel": true,
"self": 0.04857179199996153
},
"steps_from_proto": {
"total": 0.0016762340000013864,
"count": 1,
"is_parallel": true,
"self": 0.00042034499995224905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012558890000491374,
"count": 8,
"is_parallel": true,
"self": 0.0012558890000491374
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 28.0111425430008,
"count": 1896,
"is_parallel": true,
"self": 0.9636101650010005,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.7011088109990169,
"count": 1896,
"is_parallel": true,
"self": 0.7011088109990169
},
"communicator.exchange": {
"total": 23.53944270300019,
"count": 1896,
"is_parallel": true,
"self": 23.53944270300019
},
"steps_from_proto": {
"total": 2.806980864000593,
"count": 1896,
"is_parallel": true,
"self": 0.6706603650004581,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.136320499000135,
"count": 15168,
"is_parallel": true,
"self": 2.136320499000135
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 20.695863658001826,
"count": 1897,
"self": 0.05710066399944935,
"children": {
"process_trajectory": {
"total": 5.3420815480023975,
"count": 1897,
"self": 5.3420815480023975
},
"_update_policy": {
"total": 15.29668144599998,
"count": 7,
"self": 5.619010487000196,
"children": {
"TorchPPOOptimizer.update": {
"total": 9.677670958999784,
"count": 663,
"self": 9.677670958999784
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.860000662025413e-07,
"count": 1,
"self": 8.860000662025413e-07
},
"TrainerController._save_models": {
"total": 0.09930676800001947,
"count": 1,
"self": 0.002099262000001545,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09720750600001793,
"count": 1,
"self": 0.09720750600001793
}
}
}
}
}
}
}