TahsinZaman's picture
First Push
1a2d20b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.486996591091156,
"min": 0.486996591091156,
"max": 1.4242254495620728,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14750.15234375,
"min": 14540.416015625,
"max": 43205.3046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989875.0,
"min": 29952.0,
"max": 989875.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989875.0,
"min": 29952.0,
"max": 989875.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3055868446826935,
"min": -0.17805148661136627,
"max": 0.3058088421821594,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 78.8414077758789,
"min": -42.198204040527344,
"max": 78.898681640625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.12914115190505981,
"min": -0.052916597574949265,
"max": 0.3898909389972687,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 33.318416595458984,
"min": -13.440815925598145,
"max": 100.59186553955078,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06805526319507564,
"min": 0.06375051131869686,
"max": 0.0728011192433696,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9527736847310591,
"min": 0.48326776962594836,
"max": 1.0483128063982199,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017815904696625254,
"min": 7.603504979289032e-05,
"max": 0.02730087861714518,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24942266575275354,
"min": 0.0008363855477217936,
"max": 0.4095131792571777,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.340411838942861e-06,
"min": 7.340411838942861e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010276576574520006,
"min": 0.00010276576574520006,
"max": 0.0028548550483816996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244677142857146,
"min": 0.10244677142857146,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4342548000000004,
"min": 1.3886848,
"max": 2.151787,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025443246571428584,
"min": 0.00025443246571428584,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035620545200000017,
"min": 0.0035620545200000017,
"max": 0.09517666816999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013991347514092922,
"min": 0.013991347514092922,
"max": 0.5212879776954651,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19587886333465576,
"min": 0.19587886333465576,
"max": 3.6490159034729004,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 527.8035714285714,
"min": 522.1851851851852,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29557.0,
"min": 15984.0,
"max": 33458.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2243789234443714,
"min": -1.0000000521540642,
"max": 1.2243789234443714,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 69.78959863632917,
"min": -31.998401671648026,
"max": 69.78959863632917,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2243789234443714,
"min": -1.0000000521540642,
"max": 1.2243789234443714,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 69.78959863632917,
"min": -31.998401671648026,
"max": 69.78959863632917,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07805630863540021,
"min": 0.07805630863540021,
"max": 10.530504275113344,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.449209592217812,
"min": 4.279579745896626,
"max": 168.4880684018135,
"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": "1681324497",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681327984"
},
"total": 3487.0558945330004,
"count": 1,
"self": 0.6304758489986853,
"children": {
"run_training.setup": {
"total": 0.23466018500039354,
"count": 1,
"self": 0.23466018500039354
},
"TrainerController.start_learning": {
"total": 3486.1907584990013,
"count": 1,
"self": 2.604260112375414,
"children": {
"TrainerController._reset_env": {
"total": 1.528674265000518,
"count": 1,
"self": 1.528674265000518
},
"TrainerController.advance": {
"total": 3481.9336912376248,
"count": 63237,
"self": 2.8473599843418924,
"children": {
"env_step": {
"total": 2213.245194096183,
"count": 63237,
"self": 2056.6143730084177,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.03976557484384,
"count": 63237,
"self": 8.446387932655853,
"children": {
"TorchPolicy.evaluate": {
"total": 146.593377642188,
"count": 62562,
"self": 146.593377642188
}
}
},
"workers": {
"total": 1.5910555129212298,
"count": 63237,
"self": 0.0,
"children": {
"worker_root": {
"total": 3478.435804958095,
"count": 63237,
"is_parallel": true,
"self": 1611.9844212741154,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0035343939998710994,
"count": 1,
"is_parallel": true,
"self": 0.0009407769994140835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002593617000457016,
"count": 8,
"is_parallel": true,
"self": 0.002593617000457016
}
}
},
"UnityEnvironment.step": {
"total": 0.09600902500005759,
"count": 1,
"is_parallel": true,
"self": 0.0006653350001215586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000571126000068034,
"count": 1,
"is_parallel": true,
"self": 0.000571126000068034
},
"communicator.exchange": {
"total": 0.09283758299989131,
"count": 1,
"is_parallel": true,
"self": 0.09283758299989131
},
"steps_from_proto": {
"total": 0.0019349809999766876,
"count": 1,
"is_parallel": true,
"self": 0.00043154399827471934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015034370017019683,
"count": 8,
"is_parallel": true,
"self": 0.0015034370017019683
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1866.4513836839797,
"count": 63236,
"is_parallel": true,
"self": 47.77846558004876,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 29.074938155909877,
"count": 63236,
"is_parallel": true,
"self": 29.074938155909877
},
"communicator.exchange": {
"total": 1650.2552256640074,
"count": 63236,
"is_parallel": true,
"self": 1650.2552256640074
},
"steps_from_proto": {
"total": 139.3427542840136,
"count": 63236,
"is_parallel": true,
"self": 31.985894787511825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 107.35685949650178,
"count": 505888,
"is_parallel": true,
"self": 107.35685949650178
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1265.8411371571,
"count": 63237,
"self": 4.63614976419467,
"children": {
"process_trajectory": {
"total": 158.55797197491938,
"count": 63237,
"self": 158.30090148391992,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25707049099946744,
"count": 2,
"self": 0.25707049099946744
}
}
},
"_update_policy": {
"total": 1102.647015417986,
"count": 424,
"self": 438.5158481658318,
"children": {
"TorchPPOOptimizer.update": {
"total": 664.1311672521542,
"count": 22902,
"self": 664.1311672521542
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0730000212788582e-06,
"count": 1,
"self": 1.0730000212788582e-06
},
"TrainerController._save_models": {
"total": 0.12413181100055226,
"count": 1,
"self": 0.00226766299965675,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12186414800089551,
"count": 1,
"self": 0.12186414800089551
}
}
}
}
}
}
}