{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7593796253204346, "min": 1.7236061096191406, "max": 3.2956995964050293, "count": 1999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 14750.638671875, "min": 795.631103515625, "max": 105462.140625, "count": 1999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.58974358974359, "min": 42.48148148148148, "max": 999.0, "count": 1999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 10076.0, "min": 2288.0, "max": 27652.0, "count": 1999 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1649.5838475025205, "min": 1186.2026796714647, "max": 1663.4402375987613, "count": 1750 }, "SoccerTwos.Self-play.ELO.sum": { "value": 128667.5401051966, "min": 2372.4053593429294, "max": 181251.5615235925, "count": 1750 }, "SoccerTwos.Step.mean": { "value": 9999932.0, "min": 4842.0, "max": 9999932.0, "count": 2000 }, "SoccerTwos.Step.sum": { "value": 9999932.0, "min": 4842.0, "max": 9999932.0, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.018761256709694862, "min": -0.16399438679218292, "max": 0.16886329650878906, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.4633780717849731, "min": -11.807596206665039, "max": 14.52224349975586, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.017403235659003258, "min": -0.16335317492485046, "max": 0.1714138686656952, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.357452392578125, "min": -11.761428833007812, "max": 14.741592407226562, "count": 2000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0031230740058116424, "min": -0.8571428571428571, "max": 0.6503438552220663, "count": 2000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.2435997724533081, "min": -37.462000012397766, "max": 41.90520018339157, "count": 2000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0031230740058116424, "min": -0.8571428571428571, "max": 0.6503438552220663, "count": 2000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.2435997724533081, "min": -37.462000012397766, "max": 41.90520018339157, "count": 2000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012626305639666194, "min": 0.0070682897232472895, "max": 0.01800274948667114, "count": 242 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012626305639666194, "min": 0.0070682897232472895, "max": 0.01800274948667114, "count": 242 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09412251512209574, "min": 3.5354630381334576e-05, "max": 0.10630254919330279, "count": 242 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09412251512209574, "min": 3.5354630381334576e-05, "max": 0.10630254919330279, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09534507393836975, "min": 3.845273392168262e-05, "max": 0.1078297220170498, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09534507393836975, "min": 3.845273392168262e-05, "max": 0.1078297220170498, "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": "1715824929", "python_version": "3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\E:\\Users\\kibor\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715847317" }, "total": 22387.38192320001, "count": 1, "self": 1.318255699967267, "children": { "run_training.setup": { "total": 0.2477243000175804, "count": 1, "self": 0.2477243000175804 }, "TrainerController.start_learning": { "total": 22385.815943200025, "count": 1, "self": 16.207677419821266, "children": { "TrainerController._reset_env": { "total": 17.475516200152924, "count": 50, "self": 17.475516200152924 }, "TrainerController.advance": { "total": 22351.821537880023, "count": 678023, "self": 14.823673178936588, "children": { "env_step": { "total": 16284.112991010508, "count": 678023, "self": 9682.94152119814, "children": { "SubprocessEnvManager._take_step": { "total": 6590.995755400101, "count": 678023, "self": 105.5771949996415, "children": { "TorchPolicy.evaluate": { "total": 6485.41856040046, "count": 1264240, "self": 6485.41856040046 } } }, "workers": { "total": 10.175714412267553, "count": 678023, "self": 0.0, "children": { "worker_root": { "total": 22351.569669203483, "count": 678023, "is_parallel": true, "self": 14623.327197693055, "children": { "steps_from_proto": { "total": 0.10678540007211268, "count": 100, "is_parallel": true, "self": 0.01991400044062175, "children": { "_process_rank_one_or_two_observation": { "total": 0.08687139963149093, "count": 400, "is_parallel": true, "self": 0.08687139963149093 } } }, "UnityEnvironment.step": { "total": 7728.135686110356, "count": 678023, "is_parallel": true, "self": 454.7362031711382, "children": { "UnityEnvironment._generate_step_input": { "total": 378.0546937152685, "count": 678023, "is_parallel": true, "self": 378.0546937152685 }, "communicator.exchange": { "total": 5533.672232217534, "count": 678023, "is_parallel": true, "self": 5533.672232217534 }, "steps_from_proto": { "total": 1361.6725570064154, "count": 1356046, "is_parallel": true, "self": 257.7524742379319, "children": { "_process_rank_one_or_two_observation": { "total": 1103.9200827684836, "count": 5424184, "is_parallel": true, "self": 1103.9200827684836 } } } } } } } } } } }, "trainer_advance": { "total": 6052.884873690578, "count": 678023, "self": 116.62721347381012, "children": { "process_trajectory": { "total": 3313.5069570169144, "count": 678023, "self": 3307.9627687169705, "children": { "RLTrainer._checkpoint": { "total": 5.544188299943926, "count": 20, "self": 5.544188299943926 } } }, "_update_policy": { "total": 2622.750703199854, "count": 242, "self": 1623.1639057998254, "children": { "TorchPOCAOptimizer.update": { "total": 999.5867974000284, "count": 7260, "self": 999.5867974000284 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.31121080002048984, "count": 1, "self": 0.00971650000428781, "children": { "RLTrainer._checkpoint": { "total": 0.30149430001620203, "count": 1, "self": 0.30149430001620203 } } } } } } }