poca-SoccerTwos / run_logs /timers.json
JiriG's picture
First Push
cb0035a
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.1932146549224854,
"min": 1.9753402471542358,
"max": 3.2957265377044678,
"count": 1028
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 70182.8671875,
"min": 15154.88671875,
"max": 121739.0,
"count": 1028
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 590.375,
"min": 451.6666666666667,
"max": 999.0,
"count": 1028
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 18892.0,
"min": 10860.0,
"max": 29952.0,
"count": 1028
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1214.6697424666181,
"min": 1192.9066337356533,
"max": 1222.5434734996936,
"count": 258
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 2429.3394849332362,
"min": 2385.8132674713065,
"max": 14595.019604565146,
"count": 258
},
"SoccerTwos.Step.mean": {
"value": 10279221.0,
"min": 9992.0,
"max": 10279221.0,
"count": 1028
},
"SoccerTwos.Step.sum": {
"value": 10279221.0,
"min": 9992.0,
"max": 10279221.0,
"count": 1028
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.0002341218205401674,
"min": -0.10032133013010025,
"max": 0.02095644734799862,
"count": 1028
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.0037459491286426783,
"min": -1.131173849105835,
"max": 0.3372020125389099,
"count": 1028
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.0002336917823413387,
"min": -0.10030815750360489,
"max": 0.02146267145872116,
"count": 1028
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.003739068517461419,
"min": -1.1033105850219727,
"max": 0.33053696155548096,
"count": 1028
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1028
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1028
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.0,
"min": -0.6666666666666666,
"max": 0.25507691731819737,
"count": 1028
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 0.0,
"min": -10.0,
"max": 5.126399993896484,
"count": 1028
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.0,
"min": -0.6666666666666666,
"max": 0.25507691731819737,
"count": 1028
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 0.0,
"min": -10.0,
"max": 5.126399993896484,
"count": 1028
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1028
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1028
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01725513959536329,
"min": 0.00918413201313039,
"max": 0.025252745758431654,
"count": 472
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01725513959536329,
"min": 0.00918413201313039,
"max": 0.025252745758431654,
"count": 472
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 2.555828500320582e-08,
"min": 8.389954268365566e-10,
"max": 0.004824750226301452,
"count": 472
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 2.555828500320582e-08,
"min": 8.389954268365566e-10,
"max": 0.004824750226301452,
"count": 472
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 2.5823988758499895e-08,
"min": 1.0983978004919237e-09,
"max": 0.004925772765030464,
"count": 472
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 2.5823988758499895e-08,
"min": 1.0983978004919237e-09,
"max": 0.004925772765030464,
"count": 472
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 472
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 472
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 472
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000004,
"max": 0.20000000000000007,
"count": 472
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 472
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 472
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1699053147",
"python_version": "3.10.10 | packaged by conda-forge | (main, Mar 24 2023, 20:08:06) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1699080009"
},
"total": 26861.545386847,
"count": 1,
"self": 0.15334581599745434,
"children": {
"run_training.setup": {
"total": 0.041355397000074845,
"count": 1,
"self": 0.041355397000074845
},
"TrainerController.start_learning": {
"total": 26861.350685634003,
"count": 1,
"self": 19.866886405703553,
"children": {
"TrainerController._reset_env": {
"total": 10.310256601004426,
"count": 52,
"self": 10.310256601004426
},
"TrainerController.advance": {
"total": 26830.860743536294,
"count": 668805,
"self": 21.56981264440401,
"children": {
"env_step": {
"total": 22032.32335585706,
"count": 668805,
"self": 16774.87676948874,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5244.85598194,
"count": 668805,
"self": 134.98441883857777,
"children": {
"TorchPolicy.evaluate": {
"total": 5109.871563101422,
"count": 1328446,
"self": 5109.871563101422
}
}
},
"workers": {
"total": 12.590604428322195,
"count": 668805,
"self": 0.0,
"children": {
"worker_root": {
"total": 26808.834435328088,
"count": 668805,
"is_parallel": true,
"self": 12827.272152313628,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.012061035999977321,
"count": 2,
"is_parallel": true,
"self": 0.007769167999981619,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004291867999995702,
"count": 8,
"is_parallel": true,
"self": 0.004291867999995702
}
}
},
"UnityEnvironment.step": {
"total": 0.08124977900001795,
"count": 1,
"is_parallel": true,
"self": 0.0013979070000686988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000907191999999668,
"count": 1,
"is_parallel": true,
"self": 0.000907191999999668
},
"communicator.exchange": {
"total": 0.06844744900001842,
"count": 1,
"is_parallel": true,
"self": 0.06844744900001842
},
"steps_from_proto": {
"total": 0.010497230999931162,
"count": 2,
"is_parallel": true,
"self": 0.006986999999980981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0035102309999501813,
"count": 8,
"is_parallel": true,
"self": 0.0035102309999501813
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 13981.409044253454,
"count": 668804,
"is_parallel": true,
"self": 799.9046153805666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 529.8156560632366,
"count": 668804,
"is_parallel": true,
"self": 529.8156560632366
},
"communicator.exchange": {
"total": 10016.365073976402,
"count": 668804,
"is_parallel": true,
"self": 10016.365073976402
},
"steps_from_proto": {
"total": 2635.32369883325,
"count": 1337608,
"is_parallel": true,
"self": 438.07981638806905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2197.243882445181,
"count": 5350432,
"is_parallel": true,
"self": 2197.243882445181
}
}
}
}
},
"steps_from_proto": {
"total": 0.15323876100592315,
"count": 102,
"is_parallel": true,
"self": 0.029574682032034616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.12366407897388854,
"count": 408,
"is_parallel": true,
"self": 0.12366407897388854
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 4776.967575034831,
"count": 668805,
"self": 181.7714000746164,
"children": {
"process_trajectory": {
"total": 1307.0082591872133,
"count": 668805,
"self": 1301.2357325852176,
"children": {
"RLTrainer._checkpoint": {
"total": 5.772526601995651,
"count": 20,
"self": 5.772526601995651
}
}
},
"_update_policy": {
"total": 3288.187915773001,
"count": 473,
"self": 2040.4354582528347,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1247.7524575201662,
"count": 14166,
"self": 1247.7524575201662
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.434000296285376e-06,
"count": 1,
"self": 1.434000296285376e-06
},
"TrainerController._save_models": {
"total": 0.3127976569994644,
"count": 1,
"self": 0.004504037999140564,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3082936190003238,
"count": 1,
"self": 0.3082936190003238
}
}
}
}
}
}
}