yizhangliu's picture
First Push
89e1c1c
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.4425565004348755,
"min": 1.3844085931777954,
"max": 1.5574597120285034,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 28204.865234375,
"min": 23916.404296875,
"max": 34654.32421875,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 59.28048780487805,
"min": 41.610169491525426,
"max": 80.87096774193549,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19444.0,
"min": 18480.0,
"max": 20688.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1711.4192835801684,
"min": 1616.6744539808062,
"max": 1728.3371948454728,
"count": 500
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 280672.7625071476,
"min": 210761.8702068985,
"max": 387016.4449740385,
"count": 500
},
"SoccerTwos.Step.mean": {
"value": 19999996.0,
"min": 15009966.0,
"max": 19999996.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 19999996.0,
"min": 15009966.0,
"max": 19999996.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.009101184085011482,
"min": -0.12764908373355865,
"max": 0.08693856000900269,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.5016953945159912,
"min": -22.688079833984375,
"max": 15.996694564819336,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.007069459185004234,
"min": -0.124800905585289,
"max": 0.09283629804849625,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.1664607524871826,
"min": -22.838565826416016,
"max": 17.081878662109375,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.0017587896549340451,
"min": -0.34784508647257195,
"max": 0.2711822211742401,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -0.29020029306411743,
"min": -60.177199959754944,
"max": 48.81279981136322,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.0017587896549340451,
"min": -0.34784508647257195,
"max": 0.2711822211742401,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -0.29020029306411743,
"min": -60.177199959754944,
"max": 48.81279981136322,
"count": 500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01499986368289683,
"min": 0.011181827777181751,
"max": 0.02375712583695228,
"count": 242
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01499986368289683,
"min": 0.011181827777181751,
"max": 0.02375712583695228,
"count": 242
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09511033023397128,
"min": 0.0910805307328701,
"max": 0.12331863790750504,
"count": 242
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09511033023397128,
"min": 0.0910805307328701,
"max": 0.12331863790750504,
"count": 242
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09642498567700386,
"min": 0.09276533722877503,
"max": 0.1256774879992008,
"count": 242
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09642498567700386,
"min": 0.09276533722877503,
"max": 0.1256774879992008,
"count": 242
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 242
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 242
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 242
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 242
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 242
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 242
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1676020250",
"python_version": "3.9.16 (main, Feb 6 2023, 20:06:40) \n[GCC 9.3.0]",
"command_line_arguments": "/usr/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
"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": "1676047749"
},
"total": 20846.375919100014,
"count": 1,
"self": 0.32289639994269237,
"children": {
"run_training.setup": {
"total": 0.04200960003072396,
"count": 1,
"self": 0.04200960003072396
},
"TrainerController.start_learning": {
"total": 20846.01101310004,
"count": 1,
"self": 12.23138510499848,
"children": {
"TrainerController._reset_env": {
"total": 2.077954899985343,
"count": 26,
"self": 2.077954899985343
},
"TrainerController.advance": {
"total": 20830.914446595125,
"count": 347186,
"self": 13.051363897975534,
"children": {
"env_step": {
"total": 11347.175830495835,
"count": 347186,
"self": 9824.973872110422,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1514.8861284910818,
"count": 347186,
"self": 66.15480849600863,
"children": {
"TorchPolicy.evaluate": {
"total": 1448.7313199950731,
"count": 627080,
"self": 1448.7313199950731
}
}
},
"workers": {
"total": 7.315829894330818,
"count": 347186,
"self": 0.0,
"children": {
"worker_root": {
"total": 20819.18945341505,
"count": 347186,
"is_parallel": true,
"self": 12233.380375900888,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005259600060526282,
"count": 2,
"is_parallel": true,
"self": 0.0012970000389032066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003962600021623075,
"count": 8,
"is_parallel": true,
"self": 0.003962600021623075
}
}
},
"UnityEnvironment.step": {
"total": 0.05592429998796433,
"count": 1,
"is_parallel": true,
"self": 0.000904400076251477,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000763599993661046,
"count": 1,
"is_parallel": true,
"self": 0.000763599993661046
},
"communicator.exchange": {
"total": 0.050932299986016005,
"count": 1,
"is_parallel": true,
"self": 0.050932299986016005
},
"steps_from_proto": {
"total": 0.003323999932035804,
"count": 2,
"is_parallel": true,
"self": 0.000741399941034615,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025825999910011888,
"count": 8,
"is_parallel": true,
"self": 0.0025825999910011888
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.06686899991473183,
"count": 50,
"is_parallel": true,
"self": 0.014020199363585562,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.05284880055114627,
"count": 200,
"is_parallel": true,
"self": 0.05284880055114627
}
}
},
"UnityEnvironment.step": {
"total": 8585.742208514246,
"count": 347185,
"is_parallel": true,
"self": 281.55542801576667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 222.78017969988286,
"count": 347185,
"is_parallel": true,
"self": 222.78017969988286
},
"communicator.exchange": {
"total": 7223.695440103649,
"count": 347185,
"is_parallel": true,
"self": 7223.695440103649
},
"steps_from_proto": {
"total": 857.7111606949475,
"count": 694370,
"is_parallel": true,
"self": 189.3530829823576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 668.3580777125899,
"count": 2777480,
"is_parallel": true,
"self": 668.3580777125899
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 9470.687252201315,
"count": 347186,
"self": 70.71638231840916,
"children": {
"process_trajectory": {
"total": 1767.7112311830278,
"count": 347186,
"self": 1765.2458147829748,
"children": {
"RLTrainer._checkpoint": {
"total": 2.4654164000530727,
"count": 10,
"self": 2.4654164000530727
}
}
},
"_update_policy": {
"total": 7632.2596386998775,
"count": 242,
"self": 984.2722292998806,
"children": {
"TorchPOCAOptimizer.update": {
"total": 6647.987409399997,
"count": 7260,
"self": 6647.987409399997
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.8999562598764896e-06,
"count": 1,
"self": 1.8999562598764896e-06
},
"TrainerController._save_models": {
"total": 0.7872245999751613,
"count": 1,
"self": 0.001796299940906465,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7854283000342548,
"count": 1,
"self": 0.7854283000342548
}
}
}
}
}
}
}