PPO-Pyramids / run_logs /timers.json
Porridge9243's picture
First pyramids training run
eedee3f
raw
history blame
19.2 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.29516488313674927,
"min": 0.29516488313674927,
"max": 1.45228111743927,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8798.2744140625,
"min": 8798.2744140625,
"max": 44056.3984375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989907.0,
"min": 29898.0,
"max": 989907.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989907.0,
"min": 29898.0,
"max": 989907.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5003195405006409,
"min": -0.070578932762146,
"max": 0.677325963973999,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 139.08883666992188,
"min": -17.080101013183594,
"max": 196.42453002929688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.01738482341170311,
"min": -0.0632929727435112,
"max": 0.5953400135040283,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.832981109619141,
"min": -16.83592987060547,
"max": 141.0955810546875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0705662452958114,
"min": 0.06522798628499177,
"max": 0.07477385144115292,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9879274341413596,
"min": 0.5190832428670965,
"max": 1.1066284963647681,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015627442148148214,
"min": 0.0005642654813550166,
"max": 0.017924046466110406,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.218784190074075,
"min": 0.006206920294905183,
"max": 0.2509366505255457,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.581954615571426e-06,
"min": 7.581954615571426e-06,
"max": 0.0002952352301596857,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010614736461799996,
"min": 0.00010614736461799996,
"max": 0.0036329800890066996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252728571428571,
"min": 0.10252728571428571,
"max": 0.19841174285714283,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.435382,
"min": 1.3888821999999998,
"max": 2.6109933000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026247584285714283,
"min": 0.00026247584285714283,
"max": 0.00984133311142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036746618,
"min": 0.0036746618,
"max": 0.12111823067000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012240724638104439,
"min": 0.012240724638104439,
"max": 0.6664074063301086,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17137014865875244,
"min": 0.17137014865875244,
"max": 4.664851665496826,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 350.22352941176473,
"min": 274.5981308411215,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29769.0,
"min": 16697.0,
"max": 34196.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5556376299437356,
"min": -0.999987552408129,
"max": 1.7085351679060194,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 132.2291985452175,
"min": -31.999601677060127,
"max": 184.5217981338501,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5556376299437356,
"min": -0.999987552408129,
"max": 1.7085351679060194,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 132.2291985452175,
"min": -31.999601677060127,
"max": 184.5217981338501,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04430959215182263,
"min": 0.03739385766109788,
"max": 13.072795867919922,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.7663153329049237,
"min": 3.6547740946989506,
"max": 222.23752975463867,
"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": "1674992357",
"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 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": "1674994403"
},
"total": 2046.856163999,
"count": 1,
"self": 0.4445947960000467,
"children": {
"run_training.setup": {
"total": 0.09690489099989463,
"count": 1,
"self": 0.09690489099989463
},
"TrainerController.start_learning": {
"total": 2046.314664312,
"count": 1,
"self": 1.1585407410127573,
"children": {
"TrainerController._reset_env": {
"total": 5.913880348000021,
"count": 1,
"self": 5.913880348000021
},
"TrainerController.advance": {
"total": 2039.1540798139872,
"count": 64177,
"self": 1.1423318549730084,
"children": {
"env_step": {
"total": 1392.8454756659717,
"count": 64177,
"self": 1292.3194936780462,
"children": {
"SubprocessEnvManager._take_step": {
"total": 99.80697673199143,
"count": 64177,
"self": 4.06650062205199,
"children": {
"TorchPolicy.evaluate": {
"total": 95.74047610993944,
"count": 62563,
"self": 31.872515801869667,
"children": {
"TorchPolicy.sample_actions": {
"total": 63.86796030806977,
"count": 62563,
"self": 63.86796030806977
}
}
}
}
},
"workers": {
"total": 0.7190052559340074,
"count": 64177,
"self": 0.0,
"children": {
"worker_root": {
"total": 2043.2442266379517,
"count": 64177,
"is_parallel": true,
"self": 841.7056518738639,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001753784000129599,
"count": 1,
"is_parallel": true,
"self": 0.0006854969997220905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010682870004075085,
"count": 8,
"is_parallel": true,
"self": 0.0010682870004075085
}
}
},
"UnityEnvironment.step": {
"total": 0.04205558800003928,
"count": 1,
"is_parallel": true,
"self": 0.0004714500000773114,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040631199999552337,
"count": 1,
"is_parallel": true,
"self": 0.00040631199999552337
},
"communicator.exchange": {
"total": 0.039695343999937904,
"count": 1,
"is_parallel": true,
"self": 0.039695343999937904
},
"steps_from_proto": {
"total": 0.00148248200002854,
"count": 1,
"is_parallel": true,
"self": 0.0003771069996219012,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011053750004066387,
"count": 8,
"is_parallel": true,
"self": 0.0011053750004066387
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1201.5385747640878,
"count": 64176,
"is_parallel": true,
"self": 27.211734615113528,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.57723335497667,
"count": 64176,
"is_parallel": true,
"self": 21.57723335497667
},
"communicator.exchange": {
"total": 1064.9677001090208,
"count": 64176,
"is_parallel": true,
"self": 1064.9677001090208
},
"steps_from_proto": {
"total": 87.78190668497678,
"count": 64176,
"is_parallel": true,
"self": 20.188023735005345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.59388294997143,
"count": 513408,
"is_parallel": true,
"self": 67.59388294997143
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 645.1662722930425,
"count": 64177,
"self": 2.1435522999800014,
"children": {
"process_trajectory": {
"total": 139.69450990405767,
"count": 64177,
"self": 139.51114460905728,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18336529500038523,
"count": 2,
"self": 0.18336529500038523
}
}
},
"_update_policy": {
"total": 503.32821008900487,
"count": 456,
"self": 189.0508974149966,
"children": {
"TorchPPOOptimizer.update": {
"total": 314.2773126740083,
"count": 22800,
"self": 314.2773126740083
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.000000318337698e-07,
"count": 1,
"self": 9.000000318337698e-07
},
"TrainerController._save_models": {
"total": 0.08816250900008527,
"count": 1,
"self": 0.0017420899998796813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08642041900020558,
"count": 1,
"self": 0.08642041900020558
}
}
}
}
}
}
}