{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.710995078086853, "min": 1.6774101257324219, "max": 3.295762300491333, "count": 978 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35260.1875, "min": 27007.724609375, "max": 125280.015625, "count": 978 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.320754716981135, "min": 37.372093023255815, "max": 999.0, "count": 978 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 13352.0, "max": 28168.0, "count": 978 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1608.134036539323, "min": 1200.5844300827237, "max": 1654.8541914593643, "count": 974 }, "SoccerTwos.Self-play.ELO.sum": { "value": 340924.41574633645, "min": 2401.42700254753, "max": 411803.8748404472, "count": 974 }, "SoccerTwos.Step.mean": { "value": 9779982.0, "min": 9100.0, "max": 9779982.0, "count": 978 }, "SoccerTwos.Step.sum": { "value": 9779982.0, "min": 9100.0, "max": 9779982.0, "count": 978 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05798114091157913, "min": -0.13359779119491577, "max": 0.1880805939435959, "count": 978 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -12.349983215332031, "min": -25.784374237060547, "max": 34.04258728027344, "count": 978 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06252828240394592, "min": -0.13030165433883667, "max": 0.1818416863679886, "count": 978 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -13.318524360656738, "min": -25.14822006225586, "max": 32.91334533691406, "count": 978 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 978 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 978 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07543192670938555, "min": -0.6585200001796087, "max": 0.3805853593640211, "count": 978 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.06700038909912, "min": -61.1508002281189, "max": 61.52680003643036, "count": 978 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07543192670938555, "min": -0.6585200001796087, "max": 0.3805853593640211, "count": 978 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.06700038909912, "min": -61.1508002281189, "max": 61.52680003643036, "count": 978 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 978 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 978 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015312329718047598, "min": 0.011139202554719911, "max": 0.02524847324627141, "count": 473 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015312329718047598, "min": 0.011139202554719911, "max": 0.02524847324627141, "count": 473 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1099058320124944, "min": 0.0005452459969092161, "max": 0.12916857947905858, "count": 473 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1099058320124944, "min": 0.0005452459969092161, "max": 0.12916857947905858, "count": 473 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11140082428852717, "min": 0.0005458648738567717, "max": 0.13149793371558188, "count": 473 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11140082428852717, "min": 0.0005458648738567717, "max": 0.13149793371558188, "count": 473 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 473 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 473 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 473 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 473 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 473 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 473 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677098851", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Arch4ngel\\anaconda3\\envs\\deep_rl_unit_7\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --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+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1677122784" }, "total": 23932.7334446, "count": 1, "self": 4.27158519999648, "children": { "run_training.setup": { "total": 0.06711960000000028, "count": 1, "self": 0.06711960000000028 }, "TrainerController.start_learning": { "total": 23928.394739800002, "count": 1, "self": 13.663686199728545, "children": { "TrainerController._reset_env": { "total": 3.732790599990005, "count": 49, "self": 3.732790599990005 }, "TrainerController.advance": { "total": 23910.877616200287, "count": 674240, "self": 13.503123500453512, "children": { "env_step": { "total": 10277.99203849935, "count": 674240, "self": 8106.613470699167, "children": { "SubprocessEnvManager._take_step": { "total": 2162.2385546995356, "count": 674240, "self": 73.12045450000915, "children": { "TorchPolicy.evaluate": { "total": 2089.1181001995265, "count": 1230604, "self": 2089.1181001995265 } } }, "workers": { "total": 9.1400131006463, "count": 674239, "self": 0.0, "children": { "worker_root": { "total": 23905.65261890077, "count": 674239, "is_parallel": true, "self": 17309.96957660056, "children": { "steps_from_proto": { "total": 0.07255539999103178, "count": 98, "is_parallel": true, "self": 0.015662800022887335, "children": { "_process_rank_one_or_two_observation": { "total": 0.05689259996814444, "count": 392, "is_parallel": true, "self": 0.05689259996814444 } } }, "UnityEnvironment.step": { "total": 6595.610486900219, "count": 674239, "is_parallel": true, "self": 321.3176289007224, "children": { "UnityEnvironment._generate_step_input": { "total": 233.3073890999583, "count": 674239, "is_parallel": true, "self": 233.3073890999583 }, "communicator.exchange": { "total": 5034.356318600744, "count": 674239, "is_parallel": true, "self": 5034.356318600744 }, "steps_from_proto": { "total": 1006.629150298794, "count": 1348478, "is_parallel": true, "self": 213.6306938048915, "children": { "_process_rank_one_or_two_observation": { "total": 792.9984564939025, "count": 5393912, "is_parallel": true, "self": 792.9984564939025 } } } } } } } } } } }, "trainer_advance": { "total": 13619.382454200484, "count": 674239, "self": 99.0559685980952, "children": { "process_trajectory": { "total": 2397.258122502394, "count": 674239, "self": 2395.0512393023982, "children": { "RLTrainer._checkpoint": { "total": 2.206883199995673, "count": 19, "self": 2.206883199995673 } } }, "_update_policy": { "total": 11123.068363099994, "count": 473, "self": 1384.228722100037, "children": { "TorchPOCAOptimizer.update": { "total": 9738.839640999957, "count": 14190, "self": 9738.839640999957 } } } } } } }, "trainer_threads": { "total": 2.1000014385208488e-06, "count": 1, "self": 2.1000014385208488e-06 }, "TrainerController._save_models": { "total": 0.12064469999677385, "count": 1, "self": 0.0016851999971549958, "children": { "RLTrainer._checkpoint": { "total": 0.11895949999961886, "count": 1, "self": 0.11895949999961886 } } } } } } }