ZhihongDeng's picture
First Push
a2b0fb0
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 0.6666061878204346,
"min": 0.6463891267776489,
"max": 3.2958338260650635,
"count": 10000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 12350.8798828125,
"min": 632.800048828125,
"max": 376832.4375,
"count": 10000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 76.29230769230769,
"min": 35.094202898550726,
"max": 999.0,
"count": 10000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19836.0,
"min": 3692.0,
"max": 30668.0,
"count": 10000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1831.6678677537593,
"min": 1187.3317604562183,
"max": 1852.5110702140453,
"count": 9955
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 238116.8228079887,
"min": 2375.1556434615,
"max": 466622.93640783173,
"count": 9955
},
"SoccerTwos.Step.mean": {
"value": 99999989.0,
"min": 9975.0,
"max": 99999989.0,
"count": 10000
},
"SoccerTwos.Step.sum": {
"value": 99999989.0,
"min": 9975.0,
"max": 99999989.0,
"count": 10000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.01400040090084076,
"min": -0.13026683032512665,
"max": 0.1905166059732437,
"count": 10000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 1.834052562713623,
"min": -24.271142959594727,
"max": 32.21083068847656,
"count": 10000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.014650966972112656,
"min": -0.13573074340820312,
"max": 0.18502849340438843,
"count": 10000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 1.9192767143249512,
"min": -24.160072326660156,
"max": 31.156681060791016,
"count": 10000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 10000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 10000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.07949313225636956,
"min": -0.564457142991679,
"max": 0.596973911575649,
"count": 10000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 10.413600325584412,
"min": -68.68439996242523,
"max": 68.3793997168541,
"count": 10000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.07949313225636956,
"min": -0.564457142991679,
"max": 0.596973911575649,
"count": 10000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 10.413600325584412,
"min": -68.68439996242523,
"max": 68.3793997168541,
"count": 10000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.015226859835416285,
"min": 0.013034687134980535,
"max": 0.022104917299455136,
"count": 1994
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.015226859835416285,
"min": 0.013034687134980535,
"max": 0.022104917299455136,
"count": 1994
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.1041516460892227,
"min": 0.00041215566246440477,
"max": 0.122376452303595,
"count": 1994
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.1041516460892227,
"min": 0.00041215566246440477,
"max": 0.122376452303595,
"count": 1994
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10435032565146685,
"min": 0.0004121556636770644,
"max": 0.12528275191369984,
"count": 1994
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10435032565146685,
"min": 0.0004121556636770644,
"max": 0.12528275191369984,
"count": 1994
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 2.241999286004973e-09,
"min": 2.241999286004973e-09,
"max": 0.000299829744056752,
"count": 1994
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 2.241999286004973e-09,
"min": 2.241999286004973e-09,
"max": 0.000299829744056752,
"count": 1994
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.100000714,
"min": 0.100000714,
"max": 0.19994324800000005,
"count": 1994
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.100000714,
"min": 0.100000714,
"max": 0.19994324800000005,
"count": 1994
},
"SoccerTwos.Policy.Beta.mean": {
"value": 1.0035628600000084e-05,
"min": 1.0035628600000084e-05,
"max": 0.0049971680752000005,
"count": 1994
},
"SoccerTwos.Policy.Beta.sum": {
"value": 1.0035628600000084e-05,
"min": 1.0035628600000084e-05,
"max": 0.0049971680752000005,
"count": 1994
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1677049487",
"python_version": "3.9.16 (main, Jan 11 2023, 16:05:54) \n[GCC 11.2.0]",
"command_line_arguments": "/home/zhihdeng/anaconda3/envs/HuggingFaceDRL/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --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": "1677133391"
},
"total": 83904.80731506646,
"count": 1,
"self": 0.5806480310857296,
"children": {
"run_training.setup": {
"total": 0.08121960237622261,
"count": 1,
"self": 0.08121960237622261
},
"TrainerController.start_learning": {
"total": 83904.145447433,
"count": 1,
"self": 94.22289557754993,
"children": {
"TrainerController._reset_env": {
"total": 54.67632833123207,
"count": 500,
"self": 54.67632833123207
},
"TrainerController.advance": {
"total": 83754.96005585045,
"count": 4527425,
"self": 92.62372266501188,
"children": {
"env_step": {
"total": 42756.356216367334,
"count": 4527425,
"self": 13836.03085809201,
"children": {
"SubprocessEnvManager._take_step": {
"total": 28856.72142047435,
"count": 7029668,
"self": 857.1122543402016,
"children": {
"TorchPolicy.evaluate": {
"total": 27999.60916613415,
"count": 12771564,
"self": 27999.60916613415
}
}
},
"workers": {
"total": 63.603937800973654,
"count": 4527425,
"self": 0.0,
"children": {
"worker_root": {
"total": 335850.2568864301,
"count": 7028693,
"is_parallel": true,
"self": 257239.22801594436,
"children": {
"run_training.setup": {
"total": 0.32487840950489044,
"count": 4,
"is_parallel": true,
"self": 0.21821270883083344,
"children": {
"steps_from_proto": {
"total": 0.010150227695703506,
"count": 8,
"is_parallel": true,
"self": 0.0028362199664115906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.007314007729291916,
"count": 32,
"is_parallel": true,
"self": 0.007314007729291916
}
}
},
"UnityEnvironment.step": {
"total": 0.0965154729783535,
"count": 4,
"is_parallel": true,
"self": 0.0024172402918338776,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0016319416463375092,
"count": 4,
"is_parallel": true,
"self": 0.0016319416463375092
},
"communicator.exchange": {
"total": 0.08511260151863098,
"count": 4,
"is_parallel": true,
"self": 0.08511260151863098
},
"steps_from_proto": {
"total": 0.007353689521551132,
"count": 8,
"is_parallel": true,
"self": 0.0015354901552200317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0058181993663311005,
"count": 32,
"is_parallel": true,
"self": 0.0058181993663311005
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 78606.48418792337,
"count": 7028685,
"is_parallel": true,
"self": 5973.933590978384,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2846.3787834383547,
"count": 7028685,
"is_parallel": true,
"self": 2846.3787834383547
},
"communicator.exchange": {
"total": 56477.49033830315,
"count": 7028685,
"is_parallel": true,
"self": 56477.49033830315
},
"steps_from_proto": {
"total": 13308.681475203484,
"count": 14057370,
"is_parallel": true,
"self": 2520.244860779494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10788.43661442399,
"count": 56229480,
"is_parallel": true,
"self": 10788.43661442399
}
}
}
}
},
"TrainerController.start_learning": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"TrainerController._reset_env": {
"total": 87.11462037265301,
"count": 4,
"is_parallel": true,
"self": 87.11462037265301
},
"TrainerController.advance": {
"total": 525.4730990827084,
"count": 24940,
"is_parallel": true,
"self": 0.5285775065422058,
"children": {
"env_step": {
"total": 321.84629322588444,
"count": 24940,
"is_parallel": true,
"self": 105.12262518703938,
"children": {
"SubprocessEnvManager._take_step": {
"total": 216.17542307078838,
"count": 47828,
"is_parallel": true,
"self": 6.077347084879875,
"children": {
"TorchPolicy.evaluate": {
"total": 210.0980759859085,
"count": 95328,
"is_parallel": true,
"self": 210.0980759859085
}
}
},
"workers": {
"total": 0.39629462361335754,
"count": 24940,
"is_parallel": true,
"self": 0.0,
"children": {
"worker_root": {
"total": 2352.3570114970207,
"count": 47812,
"is_parallel": true,
"self": 1840.0889991819859,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.040600910782814026,
"count": 32,
"is_parallel": true,
"self": 0.011344879865646362,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.029256030917167664,
"count": 128,
"is_parallel": true,
"self": 0.029256030917167664
}
}
},
"UnityEnvironment.step": {
"total": 0.386061891913414,
"count": 16,
"is_parallel": true,
"self": 0.00966896116733551,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.006527766585350037,
"count": 16,
"is_parallel": true,
"self": 0.006527766585350037
},
"communicator.exchange": {
"total": 0.3404504060745239,
"count": 16,
"is_parallel": true,
"self": 0.3404504060745239
},
"steps_from_proto": {
"total": 0.02941475808620453,
"count": 32,
"is_parallel": true,
"self": 0.006141960620880127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.023272797465324402,
"count": 128,
"is_parallel": true,
"self": 0.023272797465324402
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 512.2680123150349,
"count": 47796,
"is_parallel": true,
"self": 27.34689722955227,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 18.028440296649933,
"count": 47796,
"is_parallel": true,
"self": 18.028440296649933
},
"communicator.exchange": {
"total": 384.59400632977486,
"count": 47796,
"is_parallel": true,
"self": 384.59400632977486
},
"steps_from_proto": {
"total": 82.29866845905781,
"count": 95592,
"is_parallel": true,
"self": 16.143723011016846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.15494544804096,
"count": 382368,
"is_parallel": true,
"self": 66.15494544804096
}
}
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.023402098566293716,
"count": 8,
"is_parallel": true,
"self": 0.004221200942993164,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.019180897623300552,
"count": 32,
"is_parallel": true,
"self": 0.019180897623300552
}
}
},
"UnityEnvironment.step": {
"total": 0.1285482458770275,
"count": 4,
"is_parallel": true,
"self": 0.013892177492380142,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.005419403314590454,
"count": 4,
"is_parallel": true,
"self": 0.005419403314590454
},
"communicator.exchange": {
"total": 0.09192324057221413,
"count": 4,
"is_parallel": true,
"self": 0.09192324057221413
},
"steps_from_proto": {
"total": 0.01731342449784279,
"count": 8,
"is_parallel": true,
"self": 0.002764381468296051,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.014549043029546738,
"count": 32,
"is_parallel": true,
"self": 0.014549043029546738
}
}
}
}
}
}
},
"trainer_advance": {
"total": 203.09822835028172,
"count": 24940,
"is_parallel": true,
"self": 7.581616789102554,
"children": {
"process_trajectory": {
"total": 52.86894811689854,
"count": 24940,
"is_parallel": true,
"self": 52.86894811689854
},
"_update_policy": {
"total": 142.64766344428062,
"count": 12,
"is_parallel": true,
"self": 93.26212346553802,
"children": {
"TorchPOCAOptimizer.update": {
"total": 49.3855399787426,
"count": 912,
"is_parallel": true,
"self": 49.3855399787426
}
}
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 4.219804152846336,
"count": 3992,
"is_parallel": true,
"self": 0.7932459115982056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.426558241248131,
"count": 15968,
"is_parallel": true,
"self": 3.426558241248131
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 40905.9801168181,
"count": 4527425,
"self": 1099.933923009783,
"children": {
"process_trajectory": {
"total": 18540.67933832854,
"count": 4527425,
"self": 18395.13620839268,
"children": {
"RLTrainer._checkpoint": {
"total": 145.54312993586063,
"count": 200,
"self": 145.54312993586063
}
}
},
"_update_policy": {
"total": 21265.366855479777,
"count": 1994,
"self": 14209.924621451646,
"children": {
"TorchPOCAOptimizer.update": {
"total": 7055.442234028131,
"count": 143631,
"self": 7055.442234028131
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.903443813323975e-07,
"count": 1,
"self": 8.903443813323975e-07
},
"TrainerController._save_models": {
"total": 0.2861667834222317,
"count": 1,
"self": 0.03692487254738808,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2492419108748436,
"count": 1,
"self": 0.2492419108748436
}
}
}
}
}
}
}