ajitgupta's picture
First Push
740039e
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.651890754699707,
"min": 0.651890754699707,
"max": 1.486037254333496,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 19588.013671875,
"min": 19588.013671875,
"max": 45080.42578125,
"count": 10
},
"Pyramids.Step.mean": {
"value": 299994.0,
"min": 29952.0,
"max": 299994.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 299994.0,
"min": 29952.0,
"max": 299994.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.052362337708473206,
"min": -0.0938456580042839,
"max": 0.15862439572811127,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -12.671686172485352,
"min": -22.616804122924805,
"max": 37.5939826965332,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.044875551015138626,
"min": 0.044875551015138626,
"max": 0.5268045663833618,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 10.859883308410645,
"min": 10.859883308410645,
"max": 124.85267639160156,
"count": 10
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06907538288237808,
"min": 0.06541385564704867,
"max": 0.07356828110307274,
"count": 10
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9670553603532931,
"min": 0.5149779677215092,
"max": 0.9733162955370014,
"count": 10
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0019092446072213499,
"min": 0.00023653851789087364,
"max": 0.01558354758518782,
"count": 10
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.026729424501098897,
"min": 0.00260192369679961,
"max": 0.10908483309631474,
"count": 10
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5030952132571428e-05,
"min": 1.5030952132571428e-05,
"max": 0.0002838354339596191,
"count": 10
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00021043332985599999,
"min": 0.00021043332985599999,
"max": 0.0027025502991500005,
"count": 10
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10501028571428574,
"min": 0.10501028571428574,
"max": 0.19461180952380958,
"count": 10
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4701440000000003,
"min": 1.362282666666667,
"max": 2.1008500000000003,
"count": 10
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0005105275428571429,
"min": 0.0005105275428571429,
"max": 0.00946171977142857,
"count": 10
},
"Pyramids.Policy.Beta.sum": {
"value": 0.007147385600000001,
"min": 0.007147385600000001,
"max": 0.09011491499999999,
"count": 10
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.039662789553403854,
"min": 0.039662789553403854,
"max": 0.6420664191246033,
"count": 10
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.5552790760993958,
"min": 0.5552790760993958,
"max": 4.494464874267578,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 975.5757575757576,
"min": 935.1764705882352,
"max": 999.0,
"count": 10
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32194.0,
"min": 15984.0,
"max": 32894.0,
"count": 10
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.7879750491119921,
"min": -1.0000000521540642,
"max": -0.5502400496602058,
"count": 10
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -25.215201571583748,
"min": -30.99780161678791,
"max": -13.756001241505146,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.7879750491119921,
"min": -1.0000000521540642,
"max": -0.5502400496602058,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -25.215201571583748,
"min": -30.99780161678791,
"max": -13.756001241505146,
"count": 10
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.40360327204689384,
"min": 0.40360327204689384,
"max": 14.68527889251709,
"count": 10
},
"Pyramids.Policy.RndReward.sum": {
"value": 12.915304705500603,
"min": 10.60102004930377,
"max": 234.96446228027344,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681571804",
"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": "1681572698"
},
"total": 893.6032623650001,
"count": 1,
"self": 0.690528474999951,
"children": {
"run_training.setup": {
"total": 0.1321402160000389,
"count": 1,
"self": 0.1321402160000389
},
"TrainerController.start_learning": {
"total": 892.7805936740001,
"count": 1,
"self": 0.6554133559880029,
"children": {
"TrainerController._reset_env": {
"total": 1.129341882999995,
"count": 1,
"self": 1.129341882999995
},
"TrainerController.advance": {
"total": 890.7331615200119,
"count": 18889,
"self": 0.7204465430172604,
"children": {
"env_step": {
"total": 572.7030447350122,
"count": 18889,
"self": 533.0104262500196,
"children": {
"SubprocessEnvManager._take_step": {
"total": 39.26509542399964,
"count": 18889,
"self": 2.021410294983241,
"children": {
"TorchPolicy.evaluate": {
"total": 37.2436851290164,
"count": 18792,
"self": 37.2436851290164
}
}
},
"workers": {
"total": 0.4275230609929963,
"count": 18889,
"self": 0.0,
"children": {
"worker_root": {
"total": 890.7464491360055,
"count": 18889,
"is_parallel": true,
"self": 405.8891057829987,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00539046099999041,
"count": 1,
"is_parallel": true,
"self": 0.003851957000051698,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015385039999387118,
"count": 8,
"is_parallel": true,
"self": 0.0015385039999387118
}
}
},
"UnityEnvironment.step": {
"total": 0.06097102000001087,
"count": 1,
"is_parallel": true,
"self": 0.0006509410000035132,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003631370000221068,
"count": 1,
"is_parallel": true,
"self": 0.0003631370000221068
},
"communicator.exchange": {
"total": 0.058054794999975456,
"count": 1,
"is_parallel": true,
"self": 0.058054794999975456
},
"steps_from_proto": {
"total": 0.0019021470000097906,
"count": 1,
"is_parallel": true,
"self": 0.000446351999869421,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014557950001403697,
"count": 8,
"is_parallel": true,
"self": 0.0014557950001403697
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 484.8573433530068,
"count": 18888,
"is_parallel": true,
"self": 13.534781928997631,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.698202629006175,
"count": 18888,
"is_parallel": true,
"self": 7.698202629006175
},
"communicator.exchange": {
"total": 425.99662395499956,
"count": 18888,
"is_parallel": true,
"self": 425.99662395499956
},
"steps_from_proto": {
"total": 37.62773484000343,
"count": 18888,
"is_parallel": true,
"self": 8.438097340014053,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.189637499989374,
"count": 151104,
"is_parallel": true,
"self": 29.189637499989374
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 317.3096702419824,
"count": 18889,
"self": 1.1125750919860025,
"children": {
"process_trajectory": {
"total": 41.15583662899695,
"count": 18889,
"self": 41.15583662899695
},
"_update_policy": {
"total": 275.04125852099946,
"count": 120,
"self": 115.1324505359982,
"children": {
"TorchPPOOptimizer.update": {
"total": 159.90880798500126,
"count": 6855,
"self": 159.90880798500126
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0840001323231263e-06,
"count": 1,
"self": 1.0840001323231263e-06
},
"TrainerController._save_models": {
"total": 0.2626758310000241,
"count": 1,
"self": 0.0018514250000407628,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26082440599998336,
"count": 1,
"self": 0.26082440599998336
}
}
}
}
}
}
}