{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7492804527282715, "min": 1.6447088718414307, "max": 3.2956857681274414, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35993.1953125, "min": 16808.376953125, "max": 282005.25, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.11267605633803, "min": 39.46341463414634, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19912.0, "min": 9512.0, "max": 30716.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1635.006448301862, "min": 1193.8427735999428, "max": 1670.0006921214163, "count": 983 }, "SoccerTwos.Self-play.ELO.sum": { "value": 232170.91565886443, "min": 2387.6855471998856, "max": 397392.9560307429, "count": 983 }, "SoccerTwos.Step.mean": { "value": 9999926.0, "min": 9102.0, "max": 9999926.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999926.0, "min": 9102.0, "max": 9999926.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02269687131047249, "min": -0.12980227172374725, "max": 0.18211790919303894, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.200258731842041, "min": -21.870420455932617, "max": 28.41156578063965, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.02401832863688469, "min": -0.13073505461215973, "max": 0.1788453310728073, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.3865842819213867, "min": -22.702056884765625, "max": 28.13270378112793, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.014286525706027417, "min": -0.5833333333333334, "max": 0.6135071414921965, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.0144001245498657, "min": -69.43879985809326, "max": 54.608399748802185, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.014286525706027417, "min": -0.5833333333333334, "max": 0.6135071414921965, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.0144001245498657, "min": -69.43879985809326, "max": 54.608399748802185, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017079885487570817, "min": 0.009205440878092, "max": 0.024769278972720108, "count": 482 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017079885487570817, "min": 0.009205440878092, "max": 0.024769278972720108, "count": 482 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08304048900802931, "min": 0.0002604979153450889, "max": 0.1260059749086698, "count": 482 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08304048900802931, "min": 0.0002604979153450889, "max": 0.1260059749086698, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08436906014879544, "min": 0.0002612599297814692, "max": 0.13014639914035797, "count": 482 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08436906014879544, "min": 0.0002612599297814692, "max": 0.13014639914035797, "count": 482 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 482 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 482 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 482 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 482 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706690957", "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\\nilsr\\.conda\\envs\\mlagents\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --num-envs=3 --force", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.23.3", "end_time_seconds": "1706703645" }, "total": 12689.3556593, "count": 1, "self": 0.518565899998066, "children": { "run_training.setup": { "total": 0.2295180999999502, "count": 1, "self": 0.2295180999999502 }, "TrainerController.start_learning": { "total": 12688.6075753, "count": 1, "self": 13.264583200225388, "children": { "TrainerController._reset_env": { "total": 7.54071139999769, "count": 50, "self": 7.54071139999769 }, "TrainerController.advance": { "total": 12667.593958599778, "count": 492104, "self": 13.851316800048153, "children": { "env_step": { "total": 7208.466190699815, "count": 492104, "self": 1558.7075056997264, "children": { "SubprocessEnvManager._take_step": { "total": 5642.456477399468, "count": 699632, "self": 95.584958599723, "children": { "TorchPolicy.evaluate": { "total": 5546.871518799745, "count": 1284461, "self": 5546.871518799745 } } }, "workers": { "total": 7.302207600620932, "count": 492103, "self": 0.0, "children": { "worker_root": { "total": 38029.594289899025, "count": 699557, "is_parallel": true, "self": 31193.259923798723, "children": { "steps_from_proto": { "total": 0.2638703000006899, "count": 300, "is_parallel": true, "self": 0.05720620000101917, "children": { "_process_rank_one_or_two_observation": { "total": 0.20666409999967073, "count": 1200, "is_parallel": true, "self": 0.20666409999967073 } } }, "UnityEnvironment.step": { "total": 6836.070495800299, "count": 699557, "is_parallel": true, "self": 375.15103440008716, "children": { "UnityEnvironment._generate_step_input": { "total": 268.7900258992204, "count": 699557, "is_parallel": true, "self": 268.7900258992204 }, "communicator.exchange": { "total": 5020.891360600281, "count": 699557, "is_parallel": true, "self": 5020.891360600281 }, "steps_from_proto": { "total": 1171.2380749007102, "count": 1399114, "is_parallel": true, "self": 258.60284860274123, "children": { "_process_rank_one_or_two_observation": { "total": 912.635226297969, "count": 5596456, "is_parallel": true, "self": 912.635226297969 } } } } } } } } } } }, "trainer_advance": { "total": 5445.276451099915, "count": 492103, "self": 107.08344929937812, "children": { "process_trajectory": { "total": 2680.497412800558, "count": 492103, "self": 2676.6741822005606, "children": { "RLTrainer._checkpoint": { "total": 3.8232305999972596, "count": 20, "self": 3.8232305999972596 } } }, "_update_policy": { "total": 2657.6955889999795, "count": 482, "self": 1410.2727498999739, "children": { "TorchPOCAOptimizer.update": { "total": 1247.4228391000056, "count": 14469, "self": 1247.4228391000056 } } } } } } }, "trainer_threads": { "total": 1.2999989849049598e-06, "count": 1, "self": 1.2999989849049598e-06 }, "TrainerController._save_models": { "total": 0.20832080000036513, "count": 1, "self": 0.006607700001040939, "children": { "RLTrainer._checkpoint": { "total": 0.20171309999932419, "count": 1, "self": 0.20171309999932419 } } } } } } }