{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4514496326446533, "min": 1.3197808265686035, "max": 3.295729637145996, "count": 4605 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28982.546875, "min": 20885.421875, "max": 124645.5078125, "count": 4605 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.19736842105263, "min": 39.08943089430894, "max": 999.0, "count": 4605 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19820.0, "min": 16140.0, "max": 26032.0, "count": 4605 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1902.078289632654, "min": 1197.7343049521035, "max": 1937.2127213221727, "count": 4554 }, "SoccerTwos.Self-play.ELO.sum": { "value": 289115.9000241634, "min": 2395.8239121441106, "max": 429609.87397075375, "count": 4554 }, "SoccerTwos.Step.mean": { "value": 46049987.0, "min": 9970.0, "max": 46049987.0, "count": 4605 }, "SoccerTwos.Step.sum": { "value": 46049987.0, "min": 9970.0, "max": 46049987.0, "count": 4605 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.027679337188601494, "min": -0.1588854342699051, "max": 0.2037215530872345, "count": 4605 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.207259178161621, "min": -31.618200302124023, "max": 28.289274215698242, "count": 4605 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.027536731213331223, "min": -0.15909075736999512, "max": 0.19906234741210938, "count": 4605 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.185583114624023, "min": -31.659059524536133, "max": 28.695724487304688, "count": 4605 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4605 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4605 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05736578961736277, "min": -0.7425999989112219, "max": 0.5727542877197266, "count": 4605 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 8.719600021839142, "min": -66.73919999599457, "max": 70.90119957923889, "count": 4605 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05736578961736277, "min": -0.7425999989112219, "max": 0.5727542877197266, "count": 4605 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 8.719600021839142, "min": -66.73919999599457, "max": 70.90119957923889, "count": 4605 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4605 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4605 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016332187781032795, "min": 0.009722032710851636, "max": 0.02553258594125509, "count": 2230 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016332187781032795, "min": 0.009722032710851636, "max": 0.02553258594125509, "count": 2230 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09716136579712233, "min": 2.0628411865194113e-06, "max": 0.12346688583493233, "count": 2230 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09716136579712233, "min": 2.0628411865194113e-06, "max": 0.12346688583493233, "count": 2230 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09787180299560229, "min": 2.1913840024960035e-06, "max": 0.12617241218686104, "count": 2230 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09787180299560229, "min": 2.1913840024960035e-06, "max": 0.12617241218686104, "count": 2230 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2230 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2230 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2230 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2230 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2230 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2230 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709930517", "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\\TE576752\\AppData\\Local\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1710077327" }, "total": 146810.34652289998, "count": 1, "self": 0.2515708999999333, "children": { "run_training.setup": { "total": 0.3718903999997565, "count": 1, "self": 0.3718903999997565 }, "TrainerController.start_learning": { "total": 146809.72306159997, "count": 1, "self": 87.84930279676337, "children": { "TrainerController._reset_env": { "total": 11.484286600094492, "count": 231, "self": 11.484286600094492 }, "TrainerController.advance": { "total": 146710.19641710314, "count": 3164035, "self": 91.90805912215728, "children": { "env_step": { "total": 61425.1935253849, "count": 3164035, "self": 47962.29276300903, "children": { "SubprocessEnvManager._take_step": { "total": 13406.549605785065, "count": 3164035, "self": 475.0261422809417, "children": { "TorchPolicy.evaluate": { "total": 12931.523463504123, "count": 5788492, "self": 12931.523463504123 } } }, "workers": { "total": 56.351156590811115, "count": 3164035, "self": 0.0, "children": { "worker_root": { "total": 146693.84032621628, "count": 3164035, "is_parallel": true, "self": 108561.78913623143, "children": { "steps_from_proto": { "total": 0.4293091999243188, "count": 462, "is_parallel": true, "self": 0.08332269923903368, "children": { "_process_rank_one_or_two_observation": { "total": 0.34598650068528514, "count": 1848, "is_parallel": true, "self": 0.34598650068528514 } } }, "UnityEnvironment.step": { "total": 38131.62188078492, "count": 3164034, "is_parallel": true, "self": 2103.0905682064404, "children": { "UnityEnvironment._generate_step_input": { "total": 1658.51511100885, "count": 3164034, "is_parallel": true, "self": 1658.51511100885 }, "communicator.exchange": { "total": 28200.717900798067, "count": 3164034, "is_parallel": true, "self": 28200.717900798067 }, "steps_from_proto": { "total": 6169.298300771569, "count": 6328068, "is_parallel": true, "self": 1199.5712652587526, "children": { "_process_rank_one_or_two_observation": { "total": 4969.727035512817, "count": 25312272, "is_parallel": true, "self": 4969.727035512817 } } } } } } } } } } }, "trainer_advance": { "total": 85193.09483259609, "count": 3164034, "self": 629.4849681738706, "children": { "process_trajectory": { "total": 13955.542832022082, "count": 3164034, "self": 13941.54434032202, "children": { "RLTrainer._checkpoint": { "total": 13.998491700062914, "count": 92, "self": 13.998491700062914 } } }, "_update_policy": { "total": 70608.06703240014, "count": 2230, "self": 6778.810363801313, "children": { "TorchPOCAOptimizer.update": { "total": 63829.25666859883, "count": 66900, "self": 63829.25666859883 } } } } } } }, "trainer_threads": { "total": 1.4999823179095984e-06, "count": 1, "self": 1.4999823179095984e-06 }, "TrainerController._save_models": { "total": 0.19305359999998473, "count": 1, "self": 0.006676999997580424, "children": { "RLTrainer._checkpoint": { "total": 0.1863766000024043, "count": 1, "self": 0.1863766000024043 } } } } } } }