{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.884081244468689, "min": 1.884081244468689, "max": 3.2957353591918945, "count": 508 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37862.49609375, "min": 28361.46875, "max": 113202.234375, "count": 508 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.10576923076923, "min": 42.18103448275862, "max": 999.0, "count": 508 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19180.0, "min": 16376.0, "max": 23500.0, "count": 508 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1602.7983110550085, "min": 1196.2323943460526, "max": 1619.4079912254106, "count": 494 }, "SoccerTwos.Self-play.ELO.sum": { "value": 333382.0486994418, "min": 2393.7028352756042, "max": 368826.2303584551, "count": 494 }, "SoccerTwos.Step.mean": { "value": 5079980.0, "min": 9708.0, "max": 5079980.0, "count": 508 }, "SoccerTwos.Step.sum": { "value": 5079980.0, "min": 9708.0, "max": 5079980.0, "count": 508 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.004579476546496153, "min": -0.09358713030815125, "max": 0.239018976688385, "count": 508 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.9571106433868408, "min": -19.653297424316406, "max": 29.63835334777832, "count": 508 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.005575027782469988, "min": -0.09068837761878967, "max": 0.24351978302001953, "count": 508 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.1651808023452759, "min": -19.044559478759766, "max": 30.196453094482422, "count": 508 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 508 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 508 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.011062200559953753, "min": -0.6153846153846154, "max": 0.5359647051960814, "count": 508 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.3119999170303345, "min": -46.457199931144714, "max": 54.73639953136444, "count": 508 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.011062200559953753, "min": -0.6153846153846154, "max": 0.5359647051960814, "count": 508 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.3119999170303345, "min": -46.457199931144714, "max": 54.73639953136444, "count": 508 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 508 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 508 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016013618178355195, "min": 0.01122971515408911, "max": 0.024642069144950558, "count": 244 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016013618178355195, "min": 0.01122971515408911, "max": 0.024642069144950558, "count": 244 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1106682501733303, "min": 4.513491406517763e-06, "max": 0.12142369697491327, "count": 244 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1106682501733303, "min": 4.513491406517763e-06, "max": 0.12142369697491327, "count": 244 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11202733889222145, "min": 3.4823727825520716e-06, "max": 0.12394256442785263, "count": 244 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11202733889222145, "min": 3.4823727825520716e-06, "max": 0.12394256442785263, "count": 244 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 244 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 244 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 244 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 244 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 244 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 244 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1712860815", "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\aambr\\OneDrive\\Documents\\Personal Projects\\Coding\\reinforcement learning\\deep-rl-course-unit7\\.venv\\Scripts\\mlagents-learn ml-agents\\config\\poca\\SoccerTwos.yaml --env=ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1712870564" }, "total": 9748.459934500002, "count": 1, "self": 0.33361809999041725, "children": { "run_training.setup": { "total": 0.08154260000446811, "count": 1, "self": 0.08154260000446811 }, "TrainerController.start_learning": { "total": 9748.044773800008, "count": 1, "self": 6.204225602734368, "children": { "TrainerController._reset_env": { "total": 9.45333289996779, "count": 26, "self": 9.45333289996779 }, "TrainerController.advance": { "total": 9732.270804997286, "count": 346921, "self": 6.107315690736868, "children": { "env_step": { "total": 4672.425207407461, "count": 346921, "self": 3540.706291707829, "children": { "SubprocessEnvManager._take_step": { "total": 1127.7238424037205, "count": 346921, "self": 35.43022109873709, "children": { "TorchPolicy.evaluate": { "total": 1092.2936213049834, "count": 641252, "self": 1092.2936213049834 } } }, "workers": { "total": 3.995073295911425, "count": 346921, "self": 0.0, "children": { "worker_root": { "total": 9721.417581599075, "count": 346921, "is_parallel": true, "self": 6870.1293640036165, "children": { "steps_from_proto": { "total": 0.03501640001195483, "count": 52, "is_parallel": true, "self": 0.007128400000510737, "children": { "_process_rank_one_or_two_observation": { "total": 0.027888000011444092, "count": 208, "is_parallel": true, "self": 0.027888000011444092 } } }, "UnityEnvironment.step": { "total": 2851.2532011954463, "count": 346921, "is_parallel": true, "self": 138.7417635840102, "children": { "UnityEnvironment._generate_step_input": { "total": 111.47159959911369, "count": 346921, "is_parallel": true, "self": 111.47159959911369 }, "communicator.exchange": { "total": 2159.3073605023674, "count": 346921, "is_parallel": true, "self": 2159.3073605023674 }, "steps_from_proto": { "total": 441.73247750995506, "count": 693842, "is_parallel": true, "self": 89.40881370550778, "children": { "_process_rank_one_or_two_observation": { "total": 352.3236638044473, "count": 2775368, "is_parallel": true, "self": 352.3236638044473 } } } } } } } } } } }, "trainer_advance": { "total": 5053.738281899088, "count": 346921, "self": 48.77761509545962, "children": { "process_trajectory": { "total": 978.6463120035769, "count": 346921, "self": 977.5362852035614, "children": { "RLTrainer._checkpoint": { "total": 1.1100268000154756, "count": 10, "self": 1.1100268000154756 } } }, "_update_policy": { "total": 4026.3143548000517, "count": 245, "self": 509.6765053005802, "children": { "TorchPOCAOptimizer.update": { "total": 3516.6378494994715, "count": 7343, "self": 3516.6378494994715 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.11640940001234412, "count": 1, "self": 0.0021212000137893483, "children": { "RLTrainer._checkpoint": { "total": 0.11428819999855477, "count": 1, "self": 0.11428819999855477 } } } } } } }