dotunadegbite's picture
Initial Run
31d3c4e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4557492434978485,
"min": 0.4447789788246155,
"max": 1.3320627212524414,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13708.9375,
"min": 13228.4033203125,
"max": 40409.453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989972.0,
"min": 29952.0,
"max": 989972.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989972.0,
"min": 29952.0,
"max": 989972.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3941933810710907,
"min": -0.10057718306779861,
"max": 0.3941933810710907,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 104.85543823242188,
"min": -24.13852310180664,
"max": 104.85543823242188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.021746771410107613,
"min": 0.00457029789686203,
"max": 0.4458710253238678,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.784641265869141,
"min": 1.1471447944641113,
"max": 107.00904846191406,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06704324098522886,
"min": 0.06513854857896349,
"max": 0.07256114784043143,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9386053737932041,
"min": 0.49042002328346357,
"max": 1.0790323386997138,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014216518126929825,
"min": 7.778141781595916e-05,
"max": 0.014216518126929825,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19903125377701755,
"min": 0.0010889398494234282,
"max": 0.2008173245897827,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.412518957764289e-06,
"min": 7.412518957764289e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010377526540870004,
"min": 0.00010377526540870004,
"max": 0.0033760783746406,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247080714285715,
"min": 0.10247080714285715,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4345913000000001,
"min": 1.3691136000000002,
"max": 2.4845616,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002568336335714287,
"min": 0.0002568336335714287,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035956708700000018,
"min": 0.0035956708700000018,
"max": 0.11255340406,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.018039723858237267,
"min": 0.018039723858237267,
"max": 0.5478460788726807,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2525561451911926,
"min": 0.2525561451911926,
"max": 3.8349225521087646,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 442.77941176470586,
"min": 442.77941176470586,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30109.0,
"min": 15984.0,
"max": 32866.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.439532332451028,
"min": -1.0000000521540642,
"max": 1.439532332451028,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 97.8881986066699,
"min": -32.000001668930054,
"max": 97.8881986066699,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.439532332451028,
"min": -1.0000000521540642,
"max": 1.439532332451028,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 97.8881986066699,
"min": -32.000001668930054,
"max": 97.8881986066699,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08312742703813403,
"min": 0.08312742703813403,
"max": 10.616564739495516,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.652665038593113,
"min": 5.652665038593113,
"max": 169.86503583192825,
"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": "1677215716",
"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": "1.22.4",
"end_time_seconds": "1677217795"
},
"total": 2078.924143927,
"count": 1,
"self": 0.5272961109999414,
"children": {
"run_training.setup": {
"total": 0.11317103600003975,
"count": 1,
"self": 0.11317103600003975
},
"TrainerController.start_learning": {
"total": 2078.28367678,
"count": 1,
"self": 1.2249490152844373,
"children": {
"TrainerController._reset_env": {
"total": 7.048068910999973,
"count": 1,
"self": 7.048068910999973
},
"TrainerController.advance": {
"total": 2069.923670041715,
"count": 63369,
"self": 1.3632009576790551,
"children": {
"env_step": {
"total": 1334.4055705281112,
"count": 63369,
"self": 1224.2088619399797,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.42746184511088,
"count": 63369,
"self": 4.528984513146952,
"children": {
"TorchPolicy.evaluate": {
"total": 104.89847733196393,
"count": 62557,
"self": 35.577166276824755,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.32131105513918,
"count": 62557,
"self": 69.32131105513918
}
}
}
}
},
"workers": {
"total": 0.7692467430206307,
"count": 63369,
"self": 0.0,
"children": {
"worker_root": {
"total": 2074.1163432331227,
"count": 63369,
"is_parallel": true,
"self": 959.473721390154,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018886120001297968,
"count": 1,
"is_parallel": true,
"self": 0.0006480279994320881,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012405840006977087,
"count": 8,
"is_parallel": true,
"self": 0.0012405840006977087
}
}
},
"UnityEnvironment.step": {
"total": 0.04611259200009954,
"count": 1,
"is_parallel": true,
"self": 0.0005266550001579162,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044880699988425476,
"count": 1,
"is_parallel": true,
"self": 0.00044880699988425476
},
"communicator.exchange": {
"total": 0.043548957999973936,
"count": 1,
"is_parallel": true,
"self": 0.043548957999973936
},
"steps_from_proto": {
"total": 0.001588172000083432,
"count": 1,
"is_parallel": true,
"self": 0.00040247199967780034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011857000004056317,
"count": 8,
"is_parallel": true,
"self": 0.0011857000004056317
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1114.6426218429688,
"count": 63368,
"is_parallel": true,
"self": 30.08884859515865,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.21092518594878,
"count": 63368,
"is_parallel": true,
"self": 22.21092518594878
},
"communicator.exchange": {
"total": 974.1453970609286,
"count": 63368,
"is_parallel": true,
"self": 974.1453970609286
},
"steps_from_proto": {
"total": 88.19745100093269,
"count": 63368,
"is_parallel": true,
"self": 20.541831242463104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.65561975846958,
"count": 506944,
"is_parallel": true,
"self": 67.65561975846958
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 734.1548985559248,
"count": 63369,
"self": 2.361128034761805,
"children": {
"process_trajectory": {
"total": 157.49187252415823,
"count": 63369,
"self": 157.3058025321584,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18606999199982965,
"count": 2,
"self": 0.18606999199982965
}
}
},
"_update_policy": {
"total": 574.3018979970047,
"count": 447,
"self": 224.06344276797927,
"children": {
"TorchPPOOptimizer.update": {
"total": 350.2384552290255,
"count": 22758,
"self": 350.2384552290255
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.560001904494129e-07,
"count": 1,
"self": 7.560001904494129e-07
},
"TrainerController._save_models": {
"total": 0.08698805600033666,
"count": 1,
"self": 0.001445390000299085,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08554266600003757,
"count": 1,
"self": 0.08554266600003757
}
}
}
}
}
}
}