{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.166483163833618, "min": 3.166483163833618, "max": 3.250258684158325, "count": 58 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48738.5078125, "min": 27737.216796875, "max": 107077.78125, "count": 58 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 875.3333333333334, "min": 511.8888888888889, "max": 999.0, "count": 58 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21008.0, "min": 7528.0, "max": 28692.0, "count": 58 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1203.9071029033946, "min": 1198.4056372665339, "max": 1206.3825205416704, "count": 53 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4815.6284116135785, "min": 2398.205874300208, "max": 12059.421115811027, "count": 53 }, "SoccerTwos.Step.mean": { "value": 1029936.0, "min": 459420.0, "max": 1029936.0, "count": 58 }, "SoccerTwos.Step.sum": { "value": 1029936.0, "min": 459420.0, "max": 1029936.0, "count": 58 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01525833923369646, "min": -0.030754486098885536, "max": 0.005721267778426409, "count": 58 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.18310007452964783, "min": -0.39520472288131714, "max": 0.06293394416570663, "count": 58 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.014285936951637268, "min": -0.031077982857823372, "max": 0.011566371656954288, "count": 58 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.17143124341964722, "min": -0.399162620306015, "max": 0.12723009288311005, "count": 58 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 58 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 58 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.12606666733821234, "min": -0.6363636363636364, "max": 0.24054286309650966, "count": 58 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.512800008058548, "min": -8.0, "max": 3.3676000833511353, "count": 58 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12606666733821234, "min": -0.6363636363636364, "max": 0.24054286309650966, "count": 58 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.512800008058548, "min": -8.0, "max": 3.3676000833511353, "count": 58 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 58 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 58 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013375023641856387, "min": 0.01290106268133968, "max": 0.02198643780623873, "count": 26 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013375023641856387, "min": 0.01290106268133968, "max": 0.02198643780623873, "count": 26 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.004635942773893476, "min": 0.0001782496049903178, "max": 0.012860427269091208, "count": 26 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.004635942773893476, "min": 0.0001782496049903178, "max": 0.012860427269091208, "count": 26 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0046321762492880225, "min": 0.0001446193697726509, "max": 0.01294019411628445, "count": 26 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0046321762492880225, "min": 0.0001446193697726509, "max": 0.01294019411628445, "count": 26 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0010000000000000002, "min": 0.001, "max": 0.0010000000000000002, "count": 26 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0010000000000000002, "min": 0.001, "max": 0.0010000000000000002, "count": 26 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10000000000000003, "min": 0.09999999999999998, "max": 0.10000000000000003, "count": 26 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10000000000000003, "min": 0.09999999999999998, "max": 0.10000000000000003, "count": 26 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 26 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 26 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675855920", "python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\noahs\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675857363" }, "total": 1442.9424357, "count": 1, "self": 1.8837830000002214, "children": { "run_training.setup": { "total": 0.0948827000000001, "count": 1, "self": 0.0948827000000001 }, "TrainerController.start_learning": { "total": 1440.9637699999998, "count": 1, "self": 0.8972267000071952, "children": { "TrainerController._reset_env": { "total": 14.781378899999966, "count": 4, "self": 14.781378899999966 }, "TrainerController.advance": { "total": 1425.1583785999926, "count": 37876, "self": 0.9655069999810166, "children": { "env_step": { "total": 600.5372935000144, "count": 37876, "self": 466.6092970000164, "children": { "SubprocessEnvManager._take_step": { "total": 133.34062279999063, "count": 37876, "self": 5.058061500023598, "children": { "TorchPolicy.evaluate": { "total": 128.28256129996703, "count": 75222, "self": 128.28256129996703 } } }, "workers": { "total": 0.5873737000073191, "count": 37875, "self": 0.0, "children": { "worker_root": { "total": 1425.2093673000145, "count": 37875, "is_parallel": true, "self": 1063.546814600024, "children": { "steps_from_proto": { "total": 0.011178599999936978, "count": 8, "is_parallel": true, "self": 0.0021064999997690848, "children": { "_process_rank_one_or_two_observation": { "total": 0.009072100000167893, "count": 32, "is_parallel": true, "self": 0.009072100000167893 } } }, "UnityEnvironment.step": { "total": 361.6513740999907, "count": 37875, "is_parallel": true, "self": 16.519696999973803, "children": { "UnityEnvironment._generate_step_input": { "total": 15.587354400002544, "count": 37875, "is_parallel": true, "self": 15.587354400002544 }, "communicator.exchange": { "total": 275.20280089999807, "count": 37875, "is_parallel": true, "self": 275.20280089999807 }, "steps_from_proto": { "total": 54.34152180001627, "count": 75750, "is_parallel": true, "self": 11.627206300025989, "children": { "_process_rank_one_or_two_observation": { "total": 42.71431549999028, "count": 303000, "is_parallel": true, "self": 42.71431549999028 } } } } } } } } } } }, "trainer_advance": { "total": 823.6555780999973, "count": 37875, "self": 6.124579700007757, "children": { "process_trajectory": { "total": 114.03539919998975, "count": 37875, "self": 113.72492339998986, "children": { "RLTrainer._checkpoint": { "total": 0.3104757999998924, "count": 2, "self": 0.3104757999998924 } } }, "_update_policy": { "total": 703.4955991999998, "count": 26, "self": 105.24513079999872, "children": { "TorchPOCAOptimizer.update": { "total": 598.2504684000011, "count": 792, "self": 598.2504684000011 } } } } } } }, "trainer_threads": { "total": 1.8000000636675395e-06, "count": 1, "self": 1.8000000636675395e-06 }, "TrainerController._save_models": { "total": 0.1267840000000433, "count": 1, "self": 0.010793000000148822, "children": { "RLTrainer._checkpoint": { "total": 0.11599099999989448, "count": 1, "self": 0.11599099999989448 } } } } } } }