{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0577354431152344, "min": 2.0551865100860596, "max": 3.2958168983459473, "count": 700 }, "SoccerTwos.Policy.Entropy.sum": { "value": 42142.421875, "min": 39130.75, "max": 101964.9453125, "count": 700 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 44.554545454545455, "min": 39.81147540983606, "max": 999.0, "count": 700 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19604.0, "min": 5600.0, "max": 32420.0, "count": 700 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1512.874655610807, "min": 1193.7859697531383, "max": 1551.9720654283042, "count": 618 }, "SoccerTwos.Self-play.ELO.sum": { "value": 332832.4242343775, "min": 2388.2305481473695, "max": 371988.25906389765, "count": 618 }, "SoccerTwos.Step.mean": { "value": 6999934.0, "min": 9976.0, "max": 6999934.0, "count": 700 }, "SoccerTwos.Step.sum": { "value": 6999934.0, "min": 9976.0, "max": 6999934.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.018976714462041855, "min": -0.12320137768983841, "max": 0.16394495964050293, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.174877166748047, "min": -23.11815643310547, "max": 26.460329055786133, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.019752051681280136, "min": -0.11610779166221619, "max": 0.1546647548675537, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.345451354980469, "min": -21.974979400634766, "max": 26.71942710876465, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0313054545359178, "min": -0.6729499995708466, "max": 0.4629948765803606, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.8871999979019165, "min": -50.458400189876556, "max": 51.514400124549866, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0313054545359178, "min": -0.6729499995708466, "max": 0.4629948765803606, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.8871999979019165, "min": -50.458400189876556, "max": 51.514400124549866, "count": 700 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017189696802718875, "min": 0.013532674185504827, "max": 0.021058293000411746, "count": 169 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017189696802718875, "min": 0.013532674185504827, "max": 0.021058293000411746, "count": 169 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1129075558235248, "min": 3.765245494946612e-07, "max": 0.1129075558235248, "count": 169 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1129075558235248, "min": 3.765245494946612e-07, "max": 0.1129075558235248, "count": 169 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1173615158845981, "min": 3.7437644143286285e-07, "max": 0.1173615158845981, "count": 169 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1173615158845981, "min": 3.7437644143286285e-07, "max": 0.1173615158845981, "count": 169 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003000000000000001, "min": 0.0003000000000000001, "max": 0.0003000000000000002, "count": 169 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003000000000000001, "min": 0.0003000000000000001, "max": 0.0003000000000000002, "count": 169 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 169 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 169 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 169 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 169 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675846488", "python_version": "3.9.10 (tags/v3.9.10:f2f3f53, Jan 17 2022, 15:14:21) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\kinkp\\Envs\\deepRL\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos.exe --run-id=poca-SoccerTwos-v4 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1675859337" }, "total": 12849.0863863, "count": 1, "self": 0.6870269000010012, "children": { "run_training.setup": { "total": 0.12990020000000024, "count": 1, "self": 0.12990020000000024 }, "TrainerController.start_learning": { "total": 12848.269459199999, "count": 1, "self": 9.995862600422697, "children": { "TrainerController._reset_env": { "total": 9.590354500000606, "count": 70, "self": 9.590354500000606 }, "TrainerController.advance": { "total": 12828.418189899576, "count": 470244, "self": 10.493732700091641, "children": { "env_step": { "total": 9559.463210899909, "count": 470244, "self": 5624.551504300496, "children": { "SubprocessEnvManager._take_step": { "total": 3928.6969822001074, "count": 470244, "self": 64.85685089988237, "children": { "TorchPolicy.evaluate": { "total": 3863.840131300225, "count": 894270, "self": 3863.840131300225 } } }, "workers": { "total": 6.214724399305011, "count": 470244, "self": 0.0, "children": { "worker_root": { "total": 12826.758375999676, "count": 470244, "is_parallel": true, "self": 8356.34454449949, "children": { "steps_from_proto": { "total": 0.12666069999624607, "count": 140, "is_parallel": true, "self": 0.026250399999383056, "children": { "_process_rank_one_or_two_observation": { "total": 0.10041029999686302, "count": 560, "is_parallel": true, "self": 0.10041029999686302 } } }, "UnityEnvironment.step": { "total": 4470.2871708001885, "count": 470244, "is_parallel": true, "self": 233.93734109980596, "children": { "UnityEnvironment._generate_step_input": { "total": 175.98905759997413, "count": 470244, "is_parallel": true, "self": 175.98905759997413 }, "communicator.exchange": { "total": 3278.8513992002354, "count": 470244, "is_parallel": true, "self": 3278.8513992002354 }, "steps_from_proto": { "total": 781.5093729001732, "count": 940488, "is_parallel": true, "self": 161.2447451008635, "children": { "_process_rank_one_or_two_observation": { "total": 620.2646277993097, "count": 3761952, "is_parallel": true, "self": 620.2646277993097 } } } } } } } } } } }, "trainer_advance": { "total": 3258.4612462995756, "count": 470244, "self": 80.79037739984597, "children": { "process_trajectory": { "total": 1318.9496275997221, "count": 470244, "self": 1315.2674705997233, "children": { "RLTrainer._checkpoint": { "total": 3.6821569999987105, "count": 14, "self": 3.6821569999987105 } } }, "_update_policy": { "total": 1858.7212413000077, "count": 169, "self": 1021.4870353000268, "children": { "TorchPOCAOptimizer.update": { "total": 837.2342059999809, "count": 10149, "self": 837.2342059999809 } } } } } } }, "trainer_threads": { "total": 6.000009307172149e-07, "count": 1, "self": 6.000009307172149e-07 }, "TrainerController._save_models": { "total": 0.26505159999942407, "count": 1, "self": 0.009057799998117844, "children": { "RLTrainer._checkpoint": { "total": 0.2559938000013062, "count": 1, "self": 0.2559938000013062 } } } } } } }