{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.840072512626648, "min": 1.5899217128753662, "max": 2.4978463649749756, "count": 761 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37390.2734375, "min": 12050.388671875, "max": 53777.86328125, "count": 761 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.142857142857146, "min": 38.196850393700785, "max": 91.75, "count": 761 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19872.0, "min": 3236.0, "max": 21184.0, "count": 761 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1529.7088135388522, "min": 1422.9264545281249, "max": 1573.7982628040145, "count": 761 }, "SoccerTwos.Self-play.ELO.sum": { "value": 256991.08067452715, "min": 42878.86507428949, "max": 382782.2583887068, "count": 761 }, "SoccerTwos.Step.mean": { "value": 10029872.0, "min": 2429979.0, "max": 10029872.0, "count": 761 }, "SoccerTwos.Step.sum": { "value": 10029872.0, "min": 2429979.0, "max": 10029872.0, "count": 761 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.031066184863448143, "min": -0.1180698424577713, "max": 0.1087309867143631, "count": 761 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.219119071960449, "min": -21.02879524230957, "max": 19.492877960205078, "count": 761 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.035260315984487534, "min": -0.11848477274179459, "max": 0.1105712503194809, "count": 761 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.923733234405518, "min": -20.94308090209961, "max": 19.144439697265625, "count": 761 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 761 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 761 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2327690479301271, "min": -0.32567314182009016, "max": 0.32442905250208337, "count": 761 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -39.10520005226135, "min": -57.35360014438629, "max": 58.072800397872925, "count": 761 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2327690479301271, "min": -0.32567314182009016, "max": 0.32442905250208337, "count": 761 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -39.10520005226135, "min": -57.35360014438629, "max": 58.072800397872925, "count": 761 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 761 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 761 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017179827320311838, "min": 0.010565199363675977, "max": 0.02532601624261588, "count": 369 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017179827320311838, "min": 0.010565199363675977, "max": 0.02532601624261588, "count": 369 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0999237209558487, "min": 0.07022709188361963, "max": 0.12925801649689675, "count": 369 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0999237209558487, "min": 0.07022709188361963, "max": 0.12925801649689675, "count": 369 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10240304668744406, "min": 0.07139496964712938, "max": 0.13219926357269288, "count": 369 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10240304668744406, "min": 0.07139496964712938, "max": 0.13219926357269288, "count": 369 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 369 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 369 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 369 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 369 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 369 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 369 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691417556", "python_version": "3.8.17 (default, Jul 5 2023, 20:44:21) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\nokot\\miniconda3\\envs\\ml-agents\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.7.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1691501578" }, "total": 84023.94156210001, "count": 1, "self": 0.33657540001149755, "children": { "run_training.setup": { "total": 0.15175470000000013, "count": 1, "self": 0.15175470000000013 }, "TrainerController.start_learning": { "total": 84023.453232, "count": 1, "self": 30.030664897349197, "children": { "TrainerController._reset_env": { "total": 10.714601099975752, "count": 39, "self": 10.714601099975752 }, "TrainerController.advance": { "total": 83982.26639350268, "count": 527687, "self": 31.88441820141452, "children": { "env_step": { "total": 21282.278971898933, "count": 527687, "self": 16135.11157879619, "children": { "SubprocessEnvManager._take_step": { "total": 5127.16464080181, "count": 527687, "self": 177.39852979446914, "children": { "TorchPolicy.evaluate": { "total": 4949.76611100734, "count": 954018, "self": 4949.76611100734 } } }, "workers": { "total": 20.002752300934617, "count": 527687, "self": 0.0, "children": { "worker_root": { "total": 83969.881665199, "count": 527687, "is_parallel": true, "self": 71320.51937559372, "children": { "steps_from_proto": { "total": 0.19051710006376155, "count": 78, "is_parallel": true, "self": 0.04021390001721237, "children": { "_process_rank_one_or_two_observation": { "total": 0.15030320004654918, "count": 312, "is_parallel": true, "self": 0.15030320004654918 } } }, "UnityEnvironment.step": { "total": 12649.171772505219, "count": 527687, "is_parallel": true, "self": 709.8374647020391, "children": { "UnityEnvironment._generate_step_input": { "total": 705.6238761024485, "count": 527687, "is_parallel": true, "self": 705.6238761024485 }, "communicator.exchange": { "total": 8715.422255598512, "count": 527687, "is_parallel": true, "self": 8715.422255598512 }, "steps_from_proto": { "total": 2518.2881761022186, "count": 1055374, "is_parallel": true, "self": 544.6141842024838, "children": { "_process_rank_one_or_two_observation": { "total": 1973.6739918997348, "count": 4221496, "is_parallel": true, "self": 1973.6739918997348 } } } } } } } } } } }, "trainer_advance": { "total": 62668.10300340233, "count": 527687, "self": 174.5810705012409, "children": { "process_trajectory": { "total": 23944.859248801124, "count": 527687, "self": 23938.519073401123, "children": { "RLTrainer._checkpoint": { "total": 6.340175399999907, "count": 16, "self": 6.340175399999907 } } }, "_update_policy": { "total": 38548.66268409997, "count": 369, "self": 2733.2539645000797, "children": { "TorchPOCAOptimizer.update": { "total": 35815.40871959989, "count": 11070, "self": 35815.40871959989 } } } } } } }, "trainer_threads": { "total": 2.7999922167509794e-06, "count": 1, "self": 2.7999922167509794e-06 }, "TrainerController._save_models": { "total": 0.44156970000767615, "count": 1, "self": 0.01958220000960864, "children": { "RLTrainer._checkpoint": { "total": 0.4219874999980675, "count": 1, "self": 0.4219874999980675 } } } } } } }