poca-SoccerTwos / run_logs /timers.json
Nebyx's picture
First Push
8d5265b
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.734297037124634,
"min": 2.661576509475708,
"max": 3.295743942260742,
"count": 109
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 57835.8515625,
"min": 21170.7578125,
"max": 124179.7109375,
"count": 109
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 104.59183673469387,
"min": 75.54545454545455,
"max": 999.0,
"count": 109
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 20500.0,
"min": 13092.0,
"max": 24912.0,
"count": 109
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1359.0160762929995,
"min": 1191.218117833444,
"max": 1359.0160762929995,
"count": 105
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 133183.57547671394,
"min": 2386.270350811539,
"max": 178575.99504405766,
"count": 105
},
"SoccerTwos.Step.mean": {
"value": 1089994.0,
"min": 9142.0,
"max": 1089994.0,
"count": 109
},
"SoccerTwos.Step.sum": {
"value": 1089994.0,
"min": 9142.0,
"max": 1089994.0,
"count": 109
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.1337754726409912,
"min": -0.01548743061721325,
"max": 0.18237759172916412,
"count": 109
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 13.10999584197998,
"min": -0.325236052274704,
"max": 19.029203414916992,
"count": 109
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.12743324041366577,
"min": -0.0147283049300313,
"max": 0.18164852261543274,
"count": 109
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 12.488457679748535,
"min": -0.3092944025993347,
"max": 18.8997802734375,
"count": 109
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 109
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 109
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.30850816259578784,
"min": -0.625,
"max": 0.5266571442286173,
"count": 109
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 30.233799934387207,
"min": -19.347999930381775,
"max": 33.83320027589798,
"count": 109
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.30850816259578784,
"min": -0.625,
"max": 0.5266571442286173,
"count": 109
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 30.233799934387207,
"min": -19.347999930381775,
"max": 33.83320027589798,
"count": 109
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 109
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 109
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01800610200618394,
"min": 0.013668357779970393,
"max": 0.024466331225412433,
"count": 51
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01800610200618394,
"min": 0.013668357779970393,
"max": 0.024466331225412433,
"count": 51
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.05764294348657131,
"min": 0.0005564878563745878,
"max": 0.05764294348657131,
"count": 51
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.05764294348657131,
"min": 0.0005564878563745878,
"max": 0.05764294348657131,
"count": 51
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.06184569776058197,
"min": 0.0006978251147666015,
"max": 0.06184569776058197,
"count": 51
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.06184569776058197,
"min": 0.0006978251147666015,
"max": 0.06184569776058197,
"count": 51
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.00030000000000000003,
"count": 51
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.00030000000000000003,
"count": 51
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.19999999999999996,
"min": 0.1999999999999999,
"max": 0.19999999999999996,
"count": 51
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.19999999999999996,
"min": 0.1999999999999999,
"max": 0.19999999999999996,
"count": 51
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 51
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 51
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1692715544",
"python_version": "3.9.17 | packaged by conda-forge | (main, Aug 10 2023, 06:55:58) [MSC v.1929 64 bit (AMD64)]",
"command_line_arguments": "\\\\?\\C:\\Users\\anado\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1692719515"
},
"total": 3971.8238017999997,
"count": 1,
"self": 0.5838407999999617,
"children": {
"run_training.setup": {
"total": 0.09870470000000031,
"count": 1,
"self": 0.09870470000000031
},
"TrainerController.start_learning": {
"total": 3971.1412563,
"count": 1,
"self": 1.5325223999407172,
"children": {
"TrainerController._reset_env": {
"total": 5.1925085000003754,
"count": 6,
"self": 5.1925085000003754
},
"TrainerController.advance": {
"total": 3964.3103379000586,
"count": 72049,
"self": 1.5927962000077969,
"children": {
"env_step": {
"total": 1029.9962354000236,
"count": 72049,
"self": 799.4769985999878,
"children": {
"SubprocessEnvManager._take_step": {
"total": 229.5688272000005,
"count": 72049,
"self": 8.965727499978243,
"children": {
"TorchPolicy.evaluate": {
"total": 220.60309970002226,
"count": 141006,
"self": 220.60309970002226
}
}
},
"workers": {
"total": 0.9504096000351803,
"count": 72048,
"self": 0.0,
"children": {
"worker_root": {
"total": 3964.1260512000836,
"count": 72048,
"is_parallel": true,
"self": 3341.96863370006,
"children": {
"steps_from_proto": {
"total": 0.010557899999221299,
"count": 12,
"is_parallel": true,
"self": 0.0020636999997947214,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008494199999426577,
"count": 48,
"is_parallel": true,
"self": 0.008494199999426577
}
}
},
"UnityEnvironment.step": {
"total": 622.1468596000245,
"count": 72048,
"is_parallel": true,
"self": 32.589318600003935,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 29.883024000037334,
"count": 72048,
"is_parallel": true,
"self": 29.883024000037334
},
"communicator.exchange": {
"total": 457.2135110999949,
"count": 72048,
"is_parallel": true,
"self": 457.2135110999949
},
"steps_from_proto": {
"total": 102.4610058999884,
"count": 144096,
"is_parallel": true,
"self": 21.4719881999809,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.9890177000075,
"count": 576384,
"is_parallel": true,
"self": 80.9890177000075
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2932.721306300027,
"count": 72048,
"self": 13.332625900000494,
"children": {
"process_trajectory": {
"total": 243.70608820002644,
"count": 72048,
"self": 243.42079240002658,
"children": {
"RLTrainer._checkpoint": {
"total": 0.285295799999858,
"count": 2,
"self": 0.285295799999858
}
}
},
"_update_policy": {
"total": 2675.6825922000003,
"count": 51,
"self": 269.6560507000054,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2406.026541499995,
"count": 2555,
"self": 2406.026541499995
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0000003385357559e-06,
"count": 1,
"self": 1.0000003385357559e-06
},
"TrainerController._save_models": {
"total": 0.10588649999999689,
"count": 1,
"self": 0.006489200000032724,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09939729999996416,
"count": 1,
"self": 0.09939729999996416
}
}
}
}
}
}
}