ppo-PyramidsRND / run_logs /timers.json
gmshuler95's picture
first training of PyramidsRND
0425119
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2585073709487915,
"min": 0.2585073709487915,
"max": 1.4580988883972168,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 7726.2685546875,
"min": 7726.2685546875,
"max": 44232.88671875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989944.0,
"min": 29952.0,
"max": 989944.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989944.0,
"min": 29952.0,
"max": 989944.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.43231913447380066,
"min": -0.08946721255779266,
"max": 0.5212188959121704,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 116.2938461303711,
"min": -21.74053192138672,
"max": 140.2078857421875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02796432189643383,
"min": -0.00023267362848855555,
"max": 0.35794275999069214,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.522402763366699,
"min": -0.05886642634868622,
"max": 84.83243560791016,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06912279901318434,
"min": 0.06581675294490133,
"max": 0.07306197815318463,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.036841985197765,
"min": 0.48637365740800853,
"max": 1.0726958547747927,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013777754162046357,
"min": 0.0011108415885338952,
"max": 0.014997458069479936,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.20666631243069536,
"min": 0.007775891119737266,
"max": 0.2099644129727191,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.453437515553337e-06,
"min": 7.453437515553337e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011180156273330006,
"min": 0.00011180156273330006,
"max": 0.0036344500885167,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248444666666669,
"min": 0.10248444666666669,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372667000000002,
"min": 1.3691136000000002,
"max": 2.6114832999999997,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002581962220000001,
"min": 0.0002581962220000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038729433300000015,
"min": 0.0038729433300000015,
"max": 0.12116718166999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013171199709177017,
"min": 0.013171199709177017,
"max": 0.4626142084598541,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19756799936294556,
"min": 0.1884431689977646,
"max": 3.2382993698120117,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 433.027397260274,
"min": 385.0933333333333,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31611.0,
"min": 15984.0,
"max": 32876.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.404391870103978,
"min": -1.0000000521540642,
"max": 1.534818891133811,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 103.92499838769436,
"min": -32.000001668930054,
"max": 121.59919797629118,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.404391870103978,
"min": -1.0000000521540642,
"max": 1.534818891133811,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 103.92499838769436,
"min": -32.000001668930054,
"max": 121.59919797629118,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05834249120734229,
"min": 0.054448635855216115,
"max": 9.064111568033695,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.31734434934333,
"min": 4.029199053285993,
"max": 145.02578508853912,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1693059118",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/home/gavin/mambaforge/envs/HuggingFace-Unit5/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1693061602"
},
"total": 2483.8159580380006,
"count": 1,
"self": 0.37165601100150525,
"children": {
"run_training.setup": {
"total": 0.011045122999348678,
"count": 1,
"self": 0.011045122999348678
},
"TrainerController.start_learning": {
"total": 2483.433256904,
"count": 1,
"self": 1.4270549550501528,
"children": {
"TrainerController._reset_env": {
"total": 0.8318113969999104,
"count": 1,
"self": 0.8318113969999104
},
"TrainerController.advance": {
"total": 2481.1030537489487,
"count": 63652,
"self": 1.1432000380818863,
"children": {
"env_step": {
"total": 1666.5598341309123,
"count": 63652,
"self": 1565.252168909139,
"children": {
"SubprocessEnvManager._take_step": {
"total": 100.41156136788777,
"count": 63652,
"self": 3.947679006092585,
"children": {
"TorchPolicy.evaluate": {
"total": 96.46388236179519,
"count": 62581,
"self": 96.46388236179519
}
}
},
"workers": {
"total": 0.8961038538855064,
"count": 63652,
"self": 0.0,
"children": {
"worker_root": {
"total": 2479.4486285640633,
"count": 63652,
"is_parallel": true,
"self": 1019.8477613499836,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014476360001935973,
"count": 1,
"is_parallel": true,
"self": 0.00040743099998508114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010402050002085161,
"count": 8,
"is_parallel": true,
"self": 0.0010402050002085161
}
}
},
"UnityEnvironment.step": {
"total": 0.046298522999677516,
"count": 1,
"is_parallel": true,
"self": 0.00037377699936769204,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003651000006357208,
"count": 1,
"is_parallel": true,
"self": 0.0003651000006357208
},
"communicator.exchange": {
"total": 0.04450906100009888,
"count": 1,
"is_parallel": true,
"self": 0.04450906100009888
},
"steps_from_proto": {
"total": 0.0010505849995752214,
"count": 1,
"is_parallel": true,
"self": 0.0002442219984004623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008063630011747591,
"count": 8,
"is_parallel": true,
"self": 0.0008063630011747591
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1459.6008672140797,
"count": 63651,
"is_parallel": true,
"self": 23.507665121027458,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 17.49720668998816,
"count": 63651,
"is_parallel": true,
"self": 17.49720668998816
},
"communicator.exchange": {
"total": 1355.8415875020482,
"count": 63651,
"is_parallel": true,
"self": 1355.8415875020482
},
"steps_from_proto": {
"total": 62.75440790101584,
"count": 63651,
"is_parallel": true,
"self": 13.537945315744764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 49.216462585271074,
"count": 509208,
"is_parallel": true,
"self": 49.216462585271074
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 813.4000195799545,
"count": 63652,
"self": 2.789292443949307,
"children": {
"process_trajectory": {
"total": 95.253193251001,
"count": 63652,
"self": 95.07386772200152,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1793255289994704,
"count": 2,
"self": 0.1793255289994704
}
}
},
"_update_policy": {
"total": 715.3575338850042,
"count": 445,
"self": 293.8911070420472,
"children": {
"TorchPPOOptimizer.update": {
"total": 421.46642684295693,
"count": 22785,
"self": 421.46642684295693
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.710004865657538e-07,
"count": 1,
"self": 7.710004865657538e-07
},
"TrainerController._save_models": {
"total": 0.07133603200054495,
"count": 1,
"self": 0.0013504840007954044,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06998554799974954,
"count": 1,
"self": 0.06998554799974954
}
}
}
}
}
}
}