{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.7792747020721436, "min": 0.7575648427009583, "max": 3.290837287902832, "count": 800 }, "SoccerTwos.Policy.Entropy.sum": { "value": 154657.96875, "min": 151003.890625, "max": 859368.375, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.74201474201474, "min": 44.82234432234432, "max": 880.6428571428571, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 197776.0, "min": 190892.0, "max": 210516.0, "count": 800 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1816.161679724213, "min": 1197.2064756132283, "max": 1863.0900931629294, "count": 800 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2956711.214591019, "min": 26407.12254297871, "max": 3610235.243623514, "count": 800 }, "SoccerTwos.Step.mean": { "value": 79999616.0, "min": 99378.0, "max": 79999616.0, "count": 800 }, "SoccerTwos.Step.sum": { "value": 79999616.0, "min": 99378.0, "max": 79999616.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.013822616077959538, "min": -0.05031982436776161, "max": 0.26127785444259644, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -22.503219604492188, "min": -80.10916137695312, "max": 473.96246337890625, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.013993286527693272, "min": -0.04985982924699783, "max": 0.2617199420928955, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -22.781070709228516, "min": -79.73173522949219, "max": 473.7984619140625, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.06194176925781025, "min": -0.19975741919009915, "max": 0.49260412219767014, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -100.84120035171509, "min": -208.66120010614395, "max": 858.0238003730774, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.06194176925781025, "min": -0.19975741919009915, "max": 0.49260412219767014, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -100.84120035171509, "min": -208.66120010614395, "max": 858.0238003730774, "count": 800 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015433308413451719, "min": 0.013221793589376224, "max": 0.020407389752557112, "count": 800 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.07716654206725859, "min": 0.057909636669016135, "max": 0.10203694876278556, "count": 800 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07788918276627858, "min": 0.0009081762121544066, "max": 0.08729567954937618, "count": 800 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.38944591383139293, "min": 0.0036327048486176263, "max": 0.4364783977468809, "count": 800 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07812579929828645, "min": 0.0009081977058788956, "max": 0.08744545966386796, "count": 800 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.39062899649143223, "min": 0.0036327908235155824, "max": 0.4372272983193398, "count": 800 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.1461094274450383e-07, "min": 1.1461094274450383e-07, "max": 0.00019985733882133065, "count": 800 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 5.730547137225191e-07, "min": 5.730547137225191e-07, "max": 0.0009969378165310926, "count": 800 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 800 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 1.25, "min": 1.0, "max": 1.25, "count": 800 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.5719824450000196e-05, "min": 1.5719824450000196e-05, "max": 0.0099928740705625, "count": 800 }, "SoccerTwos.Policy.Beta.sum": { "value": 7.859912225000097e-05, "min": 7.859912225000097e-05, "max": 0.04984704385925, "count": 800 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709796558", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/users/acp22yk/.conda/envs/RL/bin/mlagents-learn ml-agents/config/poca/SoccerTwos-002.yaml --env=ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-002 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709892541" }, "total": 95982.20562895853, "count": 1, "self": 0.3819152321666479, "children": { "run_training.setup": { "total": 0.02130541391670704, "count": 1, "self": 0.02130541391670704 }, "TrainerController.start_learning": { "total": 95981.80240831245, "count": 1, "self": 65.26715528126806, "children": { "TrainerController._reset_env": { "total": 23.127379537560046, "count": 400, "self": 23.127379537560046 }, "TrainerController.advance": { "total": 95893.19149677362, "count": 3508338, "self": 60.56081417389214, "children": { "env_step": { "total": 26319.477502632886, "count": 3508338, "self": 8655.05651905667, "children": { "SubprocessEnvManager._take_step": { "total": 17620.898139019497, "count": 5615876, "self": 596.6927085472271, "children": { "TorchPolicy.evaluate": { "total": 17024.20543047227, "count": 10232790, "self": 17024.20543047227 } } }, "workers": { "total": 43.522844556719065, "count": 3508338, "self": 0.0, "children": { "worker_root": { "total": 383711.14897011407, "count": 5615099, "is_parallel": true, "self": 335966.2943641711, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0075728148221969604, "count": 8, "is_parallel": true, "self": 0.0018653040751814842, "children": { "_process_rank_one_or_two_observation": { "total": 0.005707510747015476, "count": 32, "is_parallel": true, "self": 0.005707510747015476 } } }, "UnityEnvironment.step": { "total": 0.07662752363830805, "count": 4, "is_parallel": true, "self": 0.001918966881930828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0013922573998570442, "count": 4, "is_parallel": true, "self": 0.0013922573998570442 }, "communicator.exchange": { "total": 0.06817518267780542, "count": 4, "is_parallel": true, "self": 0.06817518267780542 }, "steps_from_proto": { "total": 0.005141116678714752, "count": 8, "is_parallel": true, "self": 0.0010620597749948502, "children": { "_process_rank_one_or_two_observation": { "total": 0.004079056903719902, "count": 32, "is_parallel": true, "self": 0.004079056903719902 } } } } } } }, "UnityEnvironment.step": { "total": 47742.73414912075, "count": 5615095, "is_parallel": true, "self": 2536.0031247790903, "children": { "UnityEnvironment._generate_step_input": { "total": 1701.2490559983999, "count": 5615095, "is_parallel": true, "self": 1701.2490559983999 }, "communicator.exchange": { "total": 36678.78153288644, "count": 5615095, "is_parallel": true, "self": 36678.78153288644 }, "steps_from_proto": { "total": 6826.70043545682, "count": 11230190, "is_parallel": true, "self": 1337.9391071666032, "children": { "_process_rank_one_or_two_observation": { "total": 5488.761328290217, "count": 44920760, "is_parallel": true, "self": 5488.761328290217 } } } } }, "steps_from_proto": { "total": 2.1204568222165108, "count": 3192, "is_parallel": true, "self": 0.40914873871952295, "children": { "_process_rank_one_or_two_observation": { "total": 1.7113080834969878, "count": 12768, "is_parallel": true, "self": 1.7113080834969878 } } } } } } } } }, "trainer_advance": { "total": 69513.15317996684, "count": 3508338, "self": 653.719340480864, "children": { "process_trajectory": { "total": 15266.808716210537, "count": 3508338, "self": 15257.60424876865, "children": { "RLTrainer._checkpoint": { "total": 9.204467441886663, "count": 40, "self": 9.204467441886663 } } }, "_update_policy": { "total": 53592.625123275444, "count": 3875, "self": 8654.569586787373, "children": { "TorchPOCAOptimizer.update": { "total": 44938.05553648807, "count": 116268, "self": 44938.05553648807 } } } } } } }, "trainer_threads": { "total": 7.133930921554565e-07, "count": 1, "self": 7.133930921554565e-07 }, "TrainerController._save_models": { "total": 0.21637600660324097, "count": 1, "self": 0.0065316092222929, "children": { "RLTrainer._checkpoint": { "total": 0.20984439738094807, "count": 1, "self": 0.20984439738094807 } } } } } } }