{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9859017133712769, "min": 1.8782767057418823, "max": 2.047666311264038, "count": 503 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43912.2578125, "min": 26401.89453125, "max": 57758.5703125, "count": 503 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 131.0810810810811, "min": 86.94736842105263, "max": 289.3529411764706, "count": 503 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19400.0, "min": 11584.0, "max": 22404.0, "count": 503 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1355.888441358503, "min": 1275.441077197799, "max": 1395.6823735516607, "count": 503 }, "SoccerTwos.Self-play.ELO.sum": { "value": 100335.74466052922, "min": 46278.77371434013, "max": 157519.3615876046, "count": 503 }, "SoccerTwos.Step.mean": { "value": 19759814.0, "min": 14739517.0, "max": 19759814.0, "count": 503 }, "SoccerTwos.Step.sum": { "value": 19759814.0, "min": 14739517.0, "max": 19759814.0, "count": 503 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03069358877837658, "min": -0.1309611052274704, "max": 0.07966340333223343, "count": 503 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.2713255882263184, "min": -9.1473388671875, "max": 7.55604887008667, "count": 503 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.031498800963163376, "min": -0.13048842549324036, "max": 0.08405119925737381, "count": 503 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.330911159515381, "min": -9.151137351989746, "max": 7.783769607543945, "count": 503 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 503 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 503 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.19556216291479162, "min": -0.495235821204399, "max": 0.3988244874136789, "count": 503 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -14.47160005569458, "min": -37.217599987983704, "max": 24.86560007929802, "count": 503 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.19556216291479162, "min": -0.495235821204399, "max": 0.3988244874136789, "count": 503 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -14.47160005569458, "min": -37.217599987983704, "max": 24.86560007929802, "count": 503 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 503 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 503 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.06393893646309153, "min": 0.03340033383501577, "max": 0.06742940049734898, "count": 242 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.06393893646309153, "min": 0.03340033383501577, "max": 0.06742940049734898, "count": 242 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.041843350138515235, "min": 0.027015811251476406, "max": 0.0498456965200603, "count": 242 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.041843350138515235, "min": 0.027015811251476406, "max": 0.0498456965200603, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.042491350695490836, "min": 0.027287230407819153, "max": 0.11414098488166928, "count": 242 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.042491350695490836, "min": 0.027287230407819153, "max": 0.11414098488166928, "count": 242 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0006, "min": 0.0006, "max": 0.0006, "count": 242 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0006, "min": 0.0006, "max": 0.0006, "count": 242 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 242 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 242 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.01, "min": 0.01, "max": 0.01, "count": 242 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.01, "min": 0.01, "max": 0.01, "count": 242 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694602557", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\bdonn\\miniconda3\\envs\\DRL\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=../Soccer/Soccer.exe --run-id=SoccerTeamBest --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1", "numpy_version": "1.25.2", "end_time_seconds": "1694614705" }, "total": 12148.1823553, "count": 1, "self": 0.009439400004339404, "children": { "run_training.setup": { "total": 0.15632360000017798, "count": 1, "self": 0.15632360000017798 }, "TrainerController.start_learning": { "total": 12148.016592299995, "count": 1, "self": 10.847635998863552, "children": { "TrainerController._reset_env": { "total": 8.639452600000368, "count": 27, "self": 8.639452600000368 }, "TrainerController.advance": { "total": 12127.91326110113, "count": 331597, "self": 8.829515205186908, "children": { "env_step": { "total": 8470.883554400643, "count": 331597, "self": 5137.614543701704, "children": { "SubprocessEnvManager._take_step": { "total": 3326.408375000523, "count": 331597, "self": 66.59249130216631, "children": { "TorchPolicy.evaluate": { "total": 3259.8158836983566, "count": 635860, "self": 3259.8158836983566 } } }, "workers": { "total": 6.860635698416445, "count": 331596, "self": 0.0, "children": { "worker_root": { "total": 12127.36054439786, "count": 331596, "is_parallel": true, "self": 8209.646047699476, "children": { "steps_from_proto": { "total": 0.05584750002162764, "count": 54, "is_parallel": true, "self": 0.0095781999771134, "children": { "_process_rank_one_or_two_observation": { "total": 0.04626930004451424, "count": 216, "is_parallel": true, "self": 0.04626930004451424 } } }, "UnityEnvironment.step": { "total": 3917.6586491983617, "count": 331596, "is_parallel": true, "self": 192.37256239513954, "children": { "UnityEnvironment._generate_step_input": { "total": 176.07630829917616, "count": 331596, "is_parallel": true, "self": 176.07630829917616 }, "communicator.exchange": { "total": 2872.249153202618, "count": 331596, "is_parallel": true, "self": 2872.249153202618 }, "steps_from_proto": { "total": 676.9606253014281, "count": 663192, "is_parallel": true, "self": 115.5395211017094, "children": { "_process_rank_one_or_two_observation": { "total": 561.4211041997187, "count": 2652768, "is_parallel": true, "self": 561.4211041997187 } } } } } } } } } } }, "trainer_advance": { "total": 3648.2001914953, "count": 331596, "self": 82.72545919418917, "children": { "process_trajectory": { "total": 999.1311738010991, "count": 331596, "self": 993.645664301097, "children": { "RLTrainer._checkpoint": { "total": 5.485509500002081, "count": 10, "self": 5.485509500002081 } } }, "_update_policy": { "total": 2566.3435585000116, "count": 242, "self": 1317.0311211999579, "children": { "TorchPOCAOptimizer.update": { "total": 1249.3124373000537, "count": 9680, "self": 1249.3124373000537 } } } } } } }, "trainer_threads": { "total": 1.3999961083754897e-06, "count": 1, "self": 1.3999961083754897e-06 }, "TrainerController._save_models": { "total": 0.6162412000048789, "count": 1, "self": 0.016175400007341523, "children": { "RLTrainer._checkpoint": { "total": 0.6000657999975374, "count": 1, "self": 0.6000657999975374 } } } } } } }