{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6575510501861572, "min": 1.4897880554199219, "max": 3.2957441806793213, "count": 1424 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32885.8125, "min": 21120.6875, "max": 120776.953125, "count": 1424 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 67.3013698630137, "min": 37.906976744186046, "max": 999.0, "count": 1424 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19652.0, "min": 12384.0, "max": 29044.0, "count": 1424 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1578.0712159703553, "min": 1190.5773214982767, "max": 1583.7762440920583, "count": 1419 }, "SoccerTwos.Self-play.ELO.sum": { "value": 230398.39753167186, "min": 2394.0430063842273, "max": 385382.60094181844, "count": 1419 }, "SoccerTwos.Step.mean": { "value": 14239964.0, "min": 9538.0, "max": 14239964.0, "count": 1424 }, "SoccerTwos.Step.sum": { "value": 14239964.0, "min": 9538.0, "max": 14239964.0, "count": 1424 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03775055706501007, "min": -0.13137996196746826, "max": 0.19136853516101837, "count": 1424 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.5115814208984375, "min": -27.66632080078125, "max": 40.95286560058594, "count": 1424 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04268205538392067, "min": -0.13336652517318726, "max": 0.19773954153060913, "count": 1424 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 6.2315802574157715, "min": -28.259611129760742, "max": 42.316261291503906, "count": 1424 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1424 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1424 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.047669863047665115, "min": -0.7955473682438758, "max": 0.5221878795912771, "count": 1424 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.9598000049591064, "min": -63.192999958992004, "max": 60.36939996480942, "count": 1424 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.047669863047665115, "min": -0.7955473682438758, "max": 0.5221878795912771, "count": 1424 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.9598000049591064, "min": -63.192999958992004, "max": 60.36939996480942, "count": 1424 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1424 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1424 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013779237668495625, "min": 0.009317553629322598, "max": 0.0257955730582277, "count": 689 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013779237668495625, "min": 0.009317553629322598, "max": 0.0257955730582277, "count": 689 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10203007906675339, "min": 0.00017220537750593697, "max": 0.13547400385141373, "count": 689 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10203007906675339, "min": 0.00017220537750593697, "max": 0.13547400385141373, "count": 689 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10406131918231647, "min": 0.0001737466242047958, "max": 0.13839883953332902, "count": 689 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10406131918231647, "min": 0.0001737466242047958, "max": 0.13839883953332902, "count": 689 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 689 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 689 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 689 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 689 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 689 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 689 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744316144", "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\\PC\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1744356352" }, "total": 40207.77201199997, "count": 1, "self": 10.014820500044152, "children": { "run_training.setup": { "total": 0.1358252998907119, "count": 1, "self": 0.1358252998907119 }, "TrainerController.start_learning": { "total": 40197.62136620004, "count": 1, "self": 26.367562427185476, "children": { "TrainerController._reset_env": { "total": 6.752045202534646, "count": 72, "self": 6.752045202534646 }, "TrainerController.advance": { "total": 40164.33305687038, "count": 990869, "self": 23.828728473745286, "children": { "env_step": { "total": 16200.938062015222, "count": 990869, "self": 12657.665366206318, "children": { "SubprocessEnvManager._take_step": { "total": 3528.306950309081, "count": 990869, "self": 125.5822390448302, "children": { "TorchPolicy.evaluate": { "total": 3402.724711264251, "count": 1790220, "self": 3402.724711264251 } } }, "workers": { "total": 14.965745499823242, "count": 990868, "self": 0.0, "children": { "worker_root": { "total": 40168.69512556563, "count": 990868, "is_parallel": true, "self": 30193.61652742466, "children": { "steps_from_proto": { "total": 0.1099320026114583, "count": 144, "is_parallel": true, "self": 0.022975101601332426, "children": { "_process_rank_one_or_two_observation": { "total": 0.08695690101012588, "count": 576, "is_parallel": true, "self": 0.08695690101012588 } } }, "UnityEnvironment.step": { "total": 9974.96866613836, "count": 990868, "is_parallel": true, "self": 419.15199332893826, "children": { "UnityEnvironment._generate_step_input": { "total": 340.00194902252406, "count": 990868, "is_parallel": true, "self": 340.00194902252406 }, "communicator.exchange": { "total": 7939.61542335758, "count": 990868, "is_parallel": true, "self": 7939.61542335758 }, "steps_from_proto": { "total": 1276.199300429318, "count": 1981736, "is_parallel": true, "self": 270.0578704185318, "children": { "_process_rank_one_or_two_observation": { "total": 1006.1414300107863, "count": 7926944, "is_parallel": true, "self": 1006.1414300107863 } } } } } } } } } } }, "trainer_advance": { "total": 23939.566266381415, "count": 990868, "self": 172.17607246595435, "children": { "process_trajectory": { "total": 3792.2650888212956, "count": 990868, "self": 3788.5565105220303, "children": { "RLTrainer._checkpoint": { "total": 3.708578299265355, "count": 28, "self": 3.708578299265355 } } }, "_update_policy": { "total": 19975.125105094165, "count": 690, "self": 2633.073051911546, "children": { "TorchPOCAOptimizer.update": { "total": 17342.05205318262, "count": 20700, "self": 17342.05205318262 } } } } } } }, "trainer_threads": { "total": 4.599802196025848e-06, "count": 1, "self": 4.599802196025848e-06 }, "TrainerController._save_models": { "total": 0.16869710013270378, "count": 1, "self": 0.017724900040775537, "children": { "RLTrainer._checkpoint": { "total": 0.15097220009192824, "count": 1, "self": 0.15097220009192824 } } } } } } }