{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6973260641098022, "min": 1.6560695171356201, "max": 3.149529457092285, "count": 765 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33457.69140625, "min": 18979.73046875, "max": 85853.65625, "count": 765 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.729166666666664, "min": 40.134453781512605, "max": 433.72727272727275, "count": 765 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19864.0, "min": 1728.0, "max": 22012.0, "count": 765 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1503.4222153489015, "min": 1198.6534959461387, "max": 1530.9758294152673, "count": 765 }, "SoccerTwos.Self-play.ELO.sum": { "value": 288657.0653469891, "min": 7210.449777128347, "max": 356989.4800138407, "count": 765 }, "SoccerTwos.Step.mean": { "value": 8639952.0, "min": 999862.0, "max": 8639952.0, "count": 765 }, "SoccerTwos.Step.sum": { "value": 8639952.0, "min": 999862.0, "max": 8639952.0, "count": 765 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.08352767676115036, "min": -0.12734852731227875, "max": 0.18192946910858154, "count": 765 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -15.95378589630127, "min": -23.941524505615234, "max": 26.015914916992188, "count": 765 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07900454849004745, "min": -0.1311393827199936, "max": 0.18299028277397156, "count": 765 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -15.089868545532227, "min": -24.654205322265625, "max": 26.41413688659668, "count": 765 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 765 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 765 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.20733821953778492, "min": -0.32395813977995586, "max": 0.875900000333786, "count": 765 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -39.60159993171692, "min": -59.902000188827515, "max": 50.295599937438965, "count": 765 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.20733821953778492, "min": -0.32395813977995586, "max": 0.875900000333786, "count": 765 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -39.60159993171692, "min": -59.902000188827515, "max": 50.295599937438965, "count": 765 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 765 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 765 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017286343254575818, "min": 0.011345698032528162, "max": 0.023778949840925635, "count": 370 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017286343254575818, "min": 0.011345698032528162, "max": 0.023778949840925635, "count": 370 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10663634488979976, "min": 0.013408512560029824, "max": 0.12825867583354314, "count": 370 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10663634488979976, "min": 0.013408512560029824, "max": 0.12825867583354314, "count": 370 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10817247877518336, "min": 0.01368649530534943, "max": 0.13054989725351335, "count": 370 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10817247877518336, "min": 0.01368649530534943, "max": 0.13054989725351335, "count": 370 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 370 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 370 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 370 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 370 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 370 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 370 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714949730", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos-0505 --no-graphics --resume --results-dir ./drive/MyDrive/ml-agents/results/", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714967350" }, "total": 17620.125808391, "count": 1, "self": 0.48291332200096804, "children": { "run_training.setup": { "total": 0.6506995189999998, "count": 1, "self": 0.6506995189999998 }, "TrainerController.start_learning": { "total": 17618.99219555, "count": 1, "self": 11.972277904234943, "children": { "TrainerController._reset_env": { "total": 8.113230823005267, "count": 40, "self": 8.113230823005267 }, "TrainerController.advance": { "total": 17598.90119277576, "count": 531961, "self": 12.901594699058478, "children": { "env_step": { "total": 13503.448067474645, "count": 531961, "self": 10433.27649414074, "children": { "SubprocessEnvManager._take_step": { "total": 3063.00353231766, "count": 531961, "self": 85.60644127860269, "children": { "TorchPolicy.evaluate": { "total": 2977.397091039057, "count": 959826, "self": 2977.397091039057 } } }, "workers": { "total": 7.168041016244274, "count": 531960, "self": 0.0, "children": { "worker_root": { "total": 17589.435670211722, "count": 531960, "is_parallel": true, "self": 8800.974009851296, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007636214999990898, "count": 2, "is_parallel": true, "self": 0.005108238000104848, "children": { "_process_rank_one_or_two_observation": { "total": 0.00252797699988605, "count": 8, "is_parallel": true, "self": 0.00252797699988605 } } }, "UnityEnvironment.step": { "total": 0.039467563000016526, "count": 1, "is_parallel": true, "self": 0.0011447839999618736, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009036370000217175, "count": 1, "is_parallel": true, "self": 0.0009036370000217175 }, "communicator.exchange": { "total": 0.03408657100004575, "count": 1, "is_parallel": true, "self": 0.03408657100004575 }, "steps_from_proto": { "total": 0.0033325709999871833, "count": 2, "is_parallel": true, "self": 0.0006172000000219668, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027153709999652165, "count": 8, "is_parallel": true, "self": 0.0027153709999652165 } } } } } } }, "steps_from_proto": { "total": 0.0916574839878308, "count": 78, "is_parallel": true, "self": 0.01781331799190866, "children": { "_process_rank_one_or_two_observation": { "total": 0.07384416599592214, "count": 312, "is_parallel": true, "self": 0.07384416599592214 } } }, "UnityEnvironment.step": { "total": 8788.370002876438, "count": 531959, "is_parallel": true, "self": 543.8803059925285, "children": { "UnityEnvironment._generate_step_input": { "total": 361.7545129028885, "count": 531959, "is_parallel": true, "self": 361.7545129028885 }, "communicator.exchange": { "total": 6157.555378543017, "count": 531959, "is_parallel": true, "self": 6157.555378543017 }, "steps_from_proto": { "total": 1725.1798054380033, "count": 1063918, "is_parallel": true, "self": 289.157194034422, "children": { "_process_rank_one_or_two_observation": { "total": 1436.0226114035813, "count": 4255672, "is_parallel": true, "self": 1436.0226114035813 } } } } } } } } } } }, "trainer_advance": { "total": 4082.5515306020584, "count": 531960, "self": 97.16858463125982, "children": { "process_trajectory": { "total": 1890.426589565792, "count": 531960, "self": 1885.1257955897956, "children": { "RLTrainer._checkpoint": { "total": 5.300793975996328, "count": 16, "self": 5.300793975996328 } } }, "_update_policy": { "total": 2094.9563564050068, "count": 371, "self": 1231.874581490914, "children": { "TorchPOCAOptimizer.update": { "total": 863.0817749140929, "count": 11130, "self": 863.0817749140929 } } } } } } }, "trainer_threads": { "total": 1.4930010365787894e-06, "count": 1, "self": 1.4930010365787894e-06 }, "TrainerController._save_models": { "total": 0.005492553998919902, "count": 1, "self": 4.1317998693557456e-05, "children": { "RLTrainer._checkpoint": { "total": 0.005451236000226345, "count": 1, "self": 0.005451236000226345 } } } } } } }