ppo-Pyramids / run_logs /timers.json
badhorse666's picture
First Push
73e99a1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5278195142745972,
"min": 0.5278195142745972,
"max": 1.4364126920700073,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15800.8046875,
"min": 15800.8046875,
"max": 43575.015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989992.0,
"min": 29952.0,
"max": 989992.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989992.0,
"min": 29952.0,
"max": 989992.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.20441554486751556,
"min": -0.1261449009180069,
"max": 0.22474543750286102,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 51.921546936035156,
"min": -29.896343231201172,
"max": 56.860595703125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.10687950253486633,
"min": -0.04446389153599739,
"max": 0.5995306968688965,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 27.14739418029785,
"min": -11.249364852905273,
"max": 142.08877563476562,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07138869741871882,
"min": 0.06626477675798524,
"max": 0.07315845825093126,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9994417638620636,
"min": 0.49176298310992245,
"max": 1.0466103729753136,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.010130189471578187,
"min": 0.0001929896710064994,
"max": 0.01673063057957968,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.14182265260209462,
"min": 0.0027018553940909916,
"max": 0.17211046302206037,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4074832451571465e-06,
"min": 7.4074832451571465e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010370476543220005,
"min": 0.00010370476543220005,
"max": 0.0035079779306740996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10246912857142858,
"min": 0.10246912857142858,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4345678000000002,
"min": 1.3886848,
"max": 2.5693259,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025666594428571445,
"min": 0.00025666594428571445,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003593323220000002,
"min": 0.003593323220000002,
"max": 0.11695565741,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.021498961374163628,
"min": 0.02144412323832512,
"max": 0.7556354403495789,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3009854555130005,
"min": 0.30021771788597107,
"max": 5.289448261260986,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 637.9787234042553,
"min": 626.5,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29985.0,
"min": 15984.0,
"max": 32656.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.8086765647885648,
"min": -1.0000000521540642,
"max": 1.0596127391178558,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 38.00779854506254,
"min": -31.996001660823822,
"max": 49.80179873853922,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.8086765647885648,
"min": -1.0000000521540642,
"max": 1.0596127391178558,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 38.00779854506254,
"min": -31.996001660823822,
"max": 49.80179873853922,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.14054739251646134,
"min": 0.14054739251646134,
"max": 15.38457228243351,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 6.605727448273683,
"min": 6.336265411548084,
"max": 246.15315651893616,
"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": "1694626799",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1694628907"
},
"total": 2107.690482931999,
"count": 1,
"self": 0.49125531199933903,
"children": {
"run_training.setup": {
"total": 0.06146721200002503,
"count": 1,
"self": 0.06146721200002503
},
"TrainerController.start_learning": {
"total": 2107.137760408,
"count": 1,
"self": 1.3415881390319555,
"children": {
"TrainerController._reset_env": {
"total": 5.138083814999845,
"count": 1,
"self": 5.138083814999845
},
"TrainerController.advance": {
"total": 2100.563999378968,
"count": 63364,
"self": 1.3308498780370428,
"children": {
"env_step": {
"total": 1435.8207583010535,
"count": 63364,
"self": 1327.7557406779697,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.24888259412819,
"count": 63364,
"self": 4.531383898172862,
"children": {
"TorchPolicy.evaluate": {
"total": 102.71749869595533,
"count": 62553,
"self": 102.71749869595533
}
}
},
"workers": {
"total": 0.816135028955614,
"count": 63364,
"self": 0.0,
"children": {
"worker_root": {
"total": 2102.1989443489283,
"count": 63364,
"is_parallel": true,
"self": 885.3251310729729,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026859259996854234,
"count": 1,
"is_parallel": true,
"self": 0.0007272630000443314,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001958662999641092,
"count": 8,
"is_parallel": true,
"self": 0.001958662999641092
}
}
},
"UnityEnvironment.step": {
"total": 0.05276346399932663,
"count": 1,
"is_parallel": true,
"self": 0.0006411099993783864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004901060001429869,
"count": 1,
"is_parallel": true,
"self": 0.0004901060001429869
},
"communicator.exchange": {
"total": 0.04861510199953045,
"count": 1,
"is_parallel": true,
"self": 0.04861510199953045
},
"steps_from_proto": {
"total": 0.0030171460002748063,
"count": 1,
"is_parallel": true,
"self": 0.00042283000129827997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025943159989765263,
"count": 8,
"is_parallel": true,
"self": 0.0025943159989765263
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1216.8738132759554,
"count": 63363,
"is_parallel": true,
"self": 33.62476700601292,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.67587602799904,
"count": 63363,
"is_parallel": true,
"self": 22.67587602799904
},
"communicator.exchange": {
"total": 1057.2867103549288,
"count": 63363,
"is_parallel": true,
"self": 1057.2867103549288
},
"steps_from_proto": {
"total": 103.28645988701464,
"count": 63363,
"is_parallel": true,
"self": 19.940933016805502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.34552687020914,
"count": 506904,
"is_parallel": true,
"self": 83.34552687020914
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 663.4123911998777,
"count": 63364,
"self": 2.5469969448931806,
"children": {
"process_trajectory": {
"total": 109.57740667198323,
"count": 63364,
"self": 109.30980270298278,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26760396900044725,
"count": 2,
"self": 0.26760396900044725
}
}
},
"_update_policy": {
"total": 551.2879875830013,
"count": 450,
"self": 358.55754943211286,
"children": {
"TorchPPOOptimizer.update": {
"total": 192.7304381508884,
"count": 22839,
"self": 192.7304381508884
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2310001693549566e-06,
"count": 1,
"self": 1.2310001693549566e-06
},
"TrainerController._save_models": {
"total": 0.09408784399965953,
"count": 1,
"self": 0.0014210529989213683,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09266679100073816,
"count": 1,
"self": 0.09266679100073816
}
}
}
}
}
}
}