{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.4995028972625732, "min": 2.4995028972625732, "max": 3.2957677841186523, "count": 200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47830.48828125, "min": 22434.65625, "max": 134064.078125, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.91463414634146, "min": 55.30337078651685, "max": 999.0, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 9692.0, "max": 31600.0, "count": 200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1426.1425062319192, "min": 1186.7099008978441, "max": 1426.1425062319192, "count": 187 }, "SoccerTwos.Self-play.ELO.sum": { "value": 233887.37102203476, "min": 2373.4198017956883, "max": 251318.45984006597, "count": 187 }, "SoccerTwos.Step.mean": { "value": 1999972.0, "min": 9816.0, "max": 1999972.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 1999972.0, "min": 9816.0, "max": 1999972.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.019718406721949577, "min": -0.10495129972696304, "max": 0.1504417061805725, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.2141003608703613, "min": -6.748437881469727, "max": 23.16802215576172, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.012798120267689228, "min": -0.10504809767007828, "max": 0.1550382673740387, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.0860936641693115, "min": -6.461188316345215, "max": 23.875892639160156, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1430552144723436, "min": -0.572771430015564, "max": 0.5919840002059936, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -23.317999958992004, "min": -32.835999846458435, "max": 47.9463996887207, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1430552144723436, "min": -0.572771430015564, "max": 0.5919840002059936, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -23.317999958992004, "min": -32.835999846458435, "max": 47.9463996887207, "count": 200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0176091943285428, "min": 0.0112602780466356, "max": 0.022041657188674436, "count": 94 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0176091943285428, "min": 0.0112602780466356, "max": 0.022041657188674436, "count": 94 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08248549650112788, "min": 4.580195563903544e-05, "max": 0.08429269219438235, "count": 94 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08248549650112788, "min": 4.580195563903544e-05, "max": 0.08429269219438235, "count": 94 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08579051742951076, "min": 4.443469200244484e-05, "max": 0.08590115283926328, "count": 94 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08579051742951076, "min": 4.443469200244484e-05, "max": 0.08590115283926328, "count": 94 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 94 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 94 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 94 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 94 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 94 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 94 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716145712", "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\\HP\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn C:/ml-agents-develop/config/poca/SoccerTwos.yaml --env=C:/ml-agents-develop/training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos0 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1716184795" }, "total": 39101.74470540008, "count": 1, "self": 0.5904948002425954, "children": { "run_training.setup": { "total": 0.1176830999320373, "count": 1, "self": 0.1176830999320373 }, "TrainerController.start_learning": { "total": 39101.036527499906, "count": 1, "self": 6.388957287184894, "children": { "TrainerController._reset_env": { "total": 7.239464999991469, "count": 10, "self": 7.239464999991469 }, "TrainerController.advance": { "total": 39087.18162571266, "count": 131498, "self": 6.725487898453139, "children": { "env_step": { "total": 10731.138303402462, "count": 131498, "self": 9572.302502990002, "children": { "SubprocessEnvManager._take_step": { "total": 1154.6130344928242, "count": 131498, "self": 40.648934202385135, "children": { "TorchPolicy.evaluate": { "total": 1113.964100290439, "count": 255240, "self": 1113.964100290439 } } }, "workers": { "total": 4.222765919636004, "count": 131498, "self": 0.0, "children": { "worker_root": { "total": 39086.81556429353, "count": 131498, "is_parallel": true, "self": 30335.635236100527, "children": { "steps_from_proto": { "total": 0.03885550005361438, "count": 20, "is_parallel": true, "self": 0.008186300401575863, "children": { "_process_rank_one_or_two_observation": { "total": 0.030669199652038515, "count": 80, "is_parallel": true, "self": 0.030669199652038515 } } }, "UnityEnvironment.step": { "total": 8751.14147269295, "count": 131498, "is_parallel": true, "self": 194.201460301294, "children": { "UnityEnvironment._generate_step_input": { "total": 206.00147668435238, "count": 131498, "is_parallel": true, "self": 206.00147668435238 }, "communicator.exchange": { "total": 7704.352328105248, "count": 131498, "is_parallel": true, "self": 7704.352328105248 }, "steps_from_proto": { "total": 646.5862076020567, "count": 262996, "is_parallel": true, "self": 123.98597489856184, "children": { "_process_rank_one_or_two_observation": { "total": 522.6002327034948, "count": 1051984, "is_parallel": true, "self": 522.6002327034948 } } } } } } } } } } }, "trainer_advance": { "total": 28349.317834411748, "count": 131498, "self": 38.030371587025, "children": { "process_trajectory": { "total": 1026.3826382248662, "count": 131498, "self": 1025.269487624988, "children": { "RLTrainer._checkpoint": { "total": 1.1131505998782814, "count": 4, "self": 1.1131505998782814 } } }, "_update_policy": { "total": 27284.904824599857, "count": 94, "self": 600.8709418027429, "children": { "TorchPOCAOptimizer.update": { "total": 26684.033882797114, "count": 2820, "self": 26684.033882797114 } } } } } } }, "trainer_threads": { "total": 2.700020559132099e-06, "count": 1, "self": 2.700020559132099e-06 }, "TrainerController._save_models": { "total": 0.22647680004592985, "count": 1, "self": 0.0030365000711753964, "children": { "RLTrainer._checkpoint": { "total": 0.22344029997475445, "count": 1, "self": 0.22344029997475445 } } } } } } }