{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.113434314727783, "min": 2.1072895526885986, "max": 3.257917881011963, "count": 485 }, "SoccerTwos.Policy.Entropy.sum": { "value": 42944.984375, "min": 17692.1171875, "max": 110909.953125, "count": 485 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.6375, "min": 41.30769230769231, "max": 999.0, "count": 485 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19404.0, "min": 7880.0, "max": 28884.0, "count": 485 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1489.4722882386639, "min": 1187.7624248316056, "max": 1489.4722882386639, "count": 441 }, "SoccerTwos.Self-play.ELO.sum": { "value": 238315.56611818622, "min": 2375.524849663211, "max": 333394.58739644464, "count": 441 }, "SoccerTwos.Step.mean": { "value": 4999960.0, "min": 159364.0, "max": 4999960.0, "count": 485 }, "SoccerTwos.Step.sum": { "value": 4999960.0, "min": 159364.0, "max": 4999960.0, "count": 485 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.011722758412361145, "min": -0.08371299505233765, "max": 0.17664726078510284, "count": 485 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.8756413459777832, "min": -14.24201774597168, "max": 24.863006591796875, "count": 485 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.011952986940741539, "min": -0.08591971546411514, "max": 0.17902688682079315, "count": 485 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.912477970123291, "min": -14.912347793579102, "max": 24.837120056152344, "count": 485 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 485 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 485 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06834750026464462, "min": -0.5625, "max": 0.6510533312956492, "count": 485 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 10.93560004234314, "min": -63.545600056648254, "max": 52.88600015640259, "count": 485 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06834750026464462, "min": -0.5625, "max": 0.6510533312956492, "count": 485 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 10.93560004234314, "min": -63.545600056648254, "max": 52.88600015640259, "count": 485 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 485 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 485 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017473193313647547, "min": 0.011169293165827791, "max": 0.02337229959666729, "count": 230 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017473193313647547, "min": 0.011169293165827791, "max": 0.02337229959666729, "count": 230 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10431629195809364, "min": 8.16802125882532e-06, "max": 0.11105090652902921, "count": 230 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10431629195809364, "min": 8.16802125882532e-06, "max": 0.11105090652902921, "count": 230 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10601297616958619, "min": 8.66735067575064e-06, "max": 0.1129910168548425, "count": 230 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10601297616958619, "min": 8.66735067575064e-06, "max": 0.1129910168548425, "count": 230 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 230 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 230 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 230 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 230 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 230 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 230 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1738505787", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/sugarblock/miniconda3/envs/mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1738513115" }, "total": 7349.475730034999, "count": 1, "self": 0.16921860999900673, "children": { "run_training.setup": { "total": 0.008424703000059708, "count": 1, "self": 0.008424703000059708 }, "TrainerController.start_learning": { "total": 7349.298086722, "count": 1, "self": 4.522663573143291, "children": { "TrainerController._reset_env": { "total": 2.100192190000712, "count": 25, "self": 2.100192190000712 }, "TrainerController.advance": { "total": 7342.578707581857, "count": 324467, "self": 4.143661259688088, "children": { "env_step": { "total": 6043.715597642181, "count": 324467, "self": 3830.026394768306, "children": { "SubprocessEnvManager._take_step": { "total": 2210.7926989668827, "count": 324467, "self": 23.673799988544943, "children": { "TorchPolicy.evaluate": { "total": 2187.1188989783377, "count": 617464, "self": 2187.1188989783377 } } }, "workers": { "total": 2.896503906992166, "count": 324467, "self": 0.0, "children": { "worker_root": { "total": 7337.583644531024, "count": 324467, "is_parallel": true, "self": 4004.070477887233, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017927119999967545, "count": 2, "is_parallel": true, "self": 0.0005602209998869512, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012324910001098033, "count": 8, "is_parallel": true, "self": 0.0012324910001098033 } } }, "UnityEnvironment.step": { "total": 0.015550956999959453, "count": 1, "is_parallel": true, "self": 0.00025352900001962553, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002797059999011253, "count": 1, "is_parallel": true, "self": 0.0002797059999011253 }, "communicator.exchange": { "total": 0.01401316199996927, "count": 1, "is_parallel": true, "self": 0.01401316199996927 }, "steps_from_proto": { "total": 0.0010045600000694321, "count": 2, "is_parallel": true, "self": 0.00022585200019875629, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007787079998706758, "count": 8, "is_parallel": true, "self": 0.0007787079998706758 } } } } } } }, "UnityEnvironment.step": { "total": 3333.4852141127913, "count": 324466, "is_parallel": true, "self": 80.79490110666757, "children": { "UnityEnvironment._generate_step_input": { "total": 50.320257560720734, "count": 324466, "is_parallel": true, "self": 50.320257560720734 }, "communicator.exchange": { "total": 2899.4052167629943, "count": 324466, "is_parallel": true, "self": 2899.4052167629943 }, "steps_from_proto": { "total": 302.964838682409, "count": 648932, "is_parallel": true, "self": 67.88240877227054, "children": { "_process_rank_one_or_two_observation": { "total": 235.08242991013844, "count": 2595728, "is_parallel": true, "self": 235.08242991013844 } } } } }, "steps_from_proto": { "total": 0.027952530999755254, "count": 48, "is_parallel": true, "self": 0.006802214003300833, "children": { "_process_rank_one_or_two_observation": { "total": 0.02115031699645442, "count": 192, "is_parallel": true, "self": 0.02115031699645442 } } } } } } } } }, "trainer_advance": { "total": 1294.7194486799885, "count": 324467, "self": 39.83793639820465, "children": { "process_trajectory": { "total": 572.8129846887837, "count": 324467, "self": 571.7352023597841, "children": { "RLTrainer._checkpoint": { "total": 1.0777823289995467, "count": 10, "self": 1.0777823289995467 } } }, "_update_policy": { "total": 682.0685275930002, "count": 230, "self": 363.5513921239933, "children": { "TorchPOCAOptimizer.update": { "total": 318.5171354690069, "count": 6912, "self": 318.5171354690069 } } } } } } }, "trainer_threads": { "total": 5.609999789157882e-07, "count": 1, "self": 5.609999789157882e-07 }, "TrainerController._save_models": { "total": 0.09652281599937851, "count": 1, "self": 0.0010266409999530879, "children": { "RLTrainer._checkpoint": { "total": 0.09549617499942542, "count": 1, "self": 0.09549617499942542 } } } } } } }