Issacwong
First Push
ffd8c63
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7478363513946533,
"min": 0.6552923321723938,
"max": 1.4892442226409912,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 22435.08984375,
"min": 19627.31640625,
"max": 45177.7109375,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479884.0,
"min": 29952.0,
"max": 479884.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479884.0,
"min": 29952.0,
"max": 479884.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.017052847892045975,
"min": -0.11444967240095139,
"max": 0.06209774315357208,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 4.195000648498535,
"min": -27.46792221069336,
"max": 14.717164993286133,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.026498693972826004,
"min": 0.02389141544699669,
"max": 0.2819814682006836,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.518678665161133,
"min": 5.805613994598389,
"max": 67.95753479003906,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06766772334092473,
"min": 0.06681067802005443,
"max": 0.07327890207168815,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9473481267729463,
"min": 0.5114851041513645,
"max": 1.025904629003634,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005663296844240828,
"min": 0.0008647587813287107,
"max": 0.005817908131996822,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.0792861558193716,
"min": 0.010377105375944528,
"max": 0.0792861558193716,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.0970264438514283e-05,
"min": 2.0970264438514283e-05,
"max": 0.00029030126037577137,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00029358370213919996,
"min": 0.00029358370213919996,
"max": 0.0030611173796275992,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10699005714285716,
"min": 0.10699005714285716,
"max": 0.19676708571428575,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4978608000000002,
"min": 1.3773696000000002,
"max": 2.3391100000000002,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007083067085714288,
"min": 0.0007083067085714288,
"max": 0.00967703186285714,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.009916293920000003,
"min": 0.009916293920000003,
"max": 0.10205520275999999,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.02381809428334236,
"min": 0.02381809428334236,
"max": 0.4806680381298065,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.33345332741737366,
"min": 0.33345332741737366,
"max": 3.3646762371063232,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 860.0285714285715,
"min": 848.2972972972973,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30101.0,
"min": 15984.0,
"max": 32929.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.17466290103537696,
"min": -1.0000000521540642,
"max": -0.17466290103537696,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -6.1132015362381935,
"min": -30.16600166261196,
"max": -6.1132015362381935,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.17466290103537696,
"min": -1.0000000521540642,
"max": -0.17466290103537696,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -6.1132015362381935,
"min": -30.16600166261196,
"max": -6.1132015362381935,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.20945755195571109,
"min": 0.20945755195571109,
"max": 9.177799014374614,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 7.331014318449888,
"min": 7.331014318449888,
"max": 146.84478422999382,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681396611",
"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": "1681397630"
},
"total": 1018.7717730460001,
"count": 1,
"self": 0.48887001900016,
"children": {
"run_training.setup": {
"total": 0.11144989500007796,
"count": 1,
"self": 0.11144989500007796
},
"TrainerController.start_learning": {
"total": 1018.1714531319999,
"count": 1,
"self": 0.7188196899901413,
"children": {
"TrainerController._reset_env": {
"total": 3.726412067999945,
"count": 1,
"self": 3.726412067999945
},
"TrainerController.advance": {
"total": 1013.6300871750102,
"count": 31595,
"self": 0.7460989870444337,
"children": {
"env_step": {
"total": 701.2927164149778,
"count": 31595,
"self": 645.6215220480162,
"children": {
"SubprocessEnvManager._take_step": {
"total": 55.25027863201126,
"count": 31595,
"self": 2.4662955799894917,
"children": {
"TorchPolicy.evaluate": {
"total": 52.78398305202177,
"count": 31318,
"self": 52.78398305202177
}
}
},
"workers": {
"total": 0.420915734950313,
"count": 31595,
"self": 0.0,
"children": {
"worker_root": {
"total": 1015.5327160730319,
"count": 31595,
"is_parallel": true,
"self": 427.05446786302764,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018344659999911528,
"count": 1,
"is_parallel": true,
"self": 0.0005916469997373497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001242819000253803,
"count": 8,
"is_parallel": true,
"self": 0.001242819000253803
}
}
},
"UnityEnvironment.step": {
"total": 0.04915285499987476,
"count": 1,
"is_parallel": true,
"self": 0.0005459579997477704,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000542612000117515,
"count": 1,
"is_parallel": true,
"self": 0.000542612000117515
},
"communicator.exchange": {
"total": 0.0463644710000608,
"count": 1,
"is_parallel": true,
"self": 0.0463644710000608
},
"steps_from_proto": {
"total": 0.0016998139999486739,
"count": 1,
"is_parallel": true,
"self": 0.0003751420001663064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013246719997823675,
"count": 8,
"is_parallel": true,
"self": 0.0013246719997823675
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 588.4782482100043,
"count": 31594,
"is_parallel": true,
"self": 16.501516454030707,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.40401675999101,
"count": 31594,
"is_parallel": true,
"self": 12.40401675999101
},
"communicator.exchange": {
"total": 509.78897090600003,
"count": 31594,
"is_parallel": true,
"self": 509.78897090600003
},
"steps_from_proto": {
"total": 49.78374408998252,
"count": 31594,
"is_parallel": true,
"self": 10.829913828054487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.95383026192803,
"count": 252752,
"is_parallel": true,
"self": 38.95383026192803
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 311.59127177298797,
"count": 31595,
"self": 1.1308382570030062,
"children": {
"process_trajectory": {
"total": 54.41532892498617,
"count": 31595,
"self": 54.30722272498633,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10810619999983828,
"count": 1,
"self": 0.10810619999983828
}
}
},
"_update_policy": {
"total": 256.0451045909988,
"count": 213,
"self": 163.4053004099983,
"children": {
"TorchPPOOptimizer.update": {
"total": 92.6398041810005,
"count": 11376,
"self": 92.6398041810005
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.7599968285067e-07,
"count": 1,
"self": 9.7599968285067e-07
},
"TrainerController._save_models": {
"total": 0.09613322299992433,
"count": 1,
"self": 0.0014119699999355362,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09472125299998879,
"count": 1,
"self": 0.09472125299998879
}
}
}
}
}
}
}