{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9099375009536743, "min": 1.8661675453186035, "max": 3.2956924438476562, "count": 502 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38993.28515625, "min": 19750.966796875, "max": 123137.859375, "count": 502 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.380434782608695, "min": 39.28225806451613, "max": 999.0, "count": 502 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19644.0, "min": 11716.0, "max": 29236.0, "count": 502 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1519.1940760052948, "min": 1193.9212761018673, "max": 1533.515514826359, "count": 474 }, "SoccerTwos.Self-play.ELO.sum": { "value": 279531.70998497424, "min": 2388.225396237318, "max": 366032.7195436335, "count": 474 }, "SoccerTwos.Step.mean": { "value": 5019975.0, "min": 9634.0, "max": 5019975.0, "count": 502 }, "SoccerTwos.Step.sum": { "value": 5019975.0, "min": 9634.0, "max": 5019975.0, "count": 502 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014535492286086082, "min": -0.08617693930864334, "max": 0.16853713989257812, "count": 502 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.674530506134033, "min": -19.663602828979492, "max": 24.766143798828125, "count": 502 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016605282202363014, "min": -0.08135741204023361, "max": 0.16739872097969055, "count": 502 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.0553717613220215, "min": -20.176637649536133, "max": 23.97747039794922, "count": 502 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 502 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 502 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.023803258719651596, "min": -0.7142857142857143, "max": 0.5368666678667069, "count": 502 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 4.3797996044158936, "min": -61.33819967508316, "max": 50.10979998111725, "count": 502 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.023803258719651596, "min": -0.7142857142857143, "max": 0.5368666678667069, "count": 502 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 4.3797996044158936, "min": -61.33819967508316, "max": 50.10979998111725, "count": 502 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 502 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 502 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015504540004379426, "min": 0.010788624302949756, "max": 0.02320948595685574, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015504540004379426, "min": 0.010788624302949756, "max": 0.02320948595685574, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10499235888322195, "min": 1.9996884664881993e-06, "max": 0.12079845145344734, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10499235888322195, "min": 1.9996884664881993e-06, "max": 0.12079845145344734, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10644705643256505, "min": 2.6293486750243272e-06, "max": 0.1227307620147864, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10644705643256505, "min": 2.6293486750243272e-06, "max": 0.1227307620147864, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715866880", "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\\Stefanos\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1715901395" }, "total": 34515.322172500004, "count": 1, "self": 2.669409000016458, "children": { "run_training.setup": { "total": 0.08809079999628011, "count": 1, "self": 0.08809079999628011 }, "TrainerController.start_learning": { "total": 34512.56467269999, "count": 1, "self": 20.805050805684004, "children": { "TrainerController._reset_env": { "total": 5.184445299993968, "count": 26, "self": 5.184445299993968 }, "TrainerController.advance": { "total": 34486.22540859431, "count": 342100, "self": 23.311311696874327, "children": { "env_step": { "total": 13792.796540091826, "count": 342100, "self": 9704.924439886265, "children": { "SubprocessEnvManager._take_step": { "total": 4074.3288993037495, "count": 342100, "self": 140.05613029219967, "children": { "TorchPolicy.evaluate": { "total": 3934.27276901155, "count": 634252, "self": 3934.27276901155 } } }, "workers": { "total": 13.54320090181136, "count": 342099, "self": 0.0, "children": { "worker_root": { "total": 34481.35648600158, "count": 342099, "is_parallel": true, "self": 27277.232640405367, "children": { "steps_from_proto": { "total": 0.12828029996308032, "count": 52, "is_parallel": true, "self": 0.026462799905857537, "children": { "_process_rank_one_or_two_observation": { "total": 0.10181750005722279, "count": 208, "is_parallel": true, "self": 0.10181750005722279 } } }, "UnityEnvironment.step": { "total": 7203.995565296253, "count": 342099, "is_parallel": true, "self": 511.52673209626664, "children": { "UnityEnvironment._generate_step_input": { "total": 464.5084292975662, "count": 342099, "is_parallel": true, "self": 464.5084292975662 }, "communicator.exchange": { "total": 4619.977792499427, "count": 342099, "is_parallel": true, "self": 4619.977792499427 }, "steps_from_proto": { "total": 1607.982611402993, "count": 684198, "is_parallel": true, "self": 334.3732184034452, "children": { "_process_rank_one_or_two_observation": { "total": 1273.6093929995477, "count": 2736792, "is_parallel": true, "self": 1273.6093929995477 } } } } } } } } } } }, "trainer_advance": { "total": 20670.117556805613, "count": 342099, "self": 126.89241390427196, "children": { "process_trajectory": { "total": 4399.967536801341, "count": 342099, "self": 4396.0436804013225, "children": { "RLTrainer._checkpoint": { "total": 3.923856400018849, "count": 10, "self": 3.923856400018849 } } }, "_update_policy": { "total": 16143.2576061, "count": 241, "self": 2189.836036298977, "children": { "TorchPOCAOptimizer.update": { "total": 13953.421569801023, "count": 7230, "self": 13953.421569801023 } } } } } } }, "trainer_threads": { "total": 2.2000021999701858e-06, "count": 1, "self": 2.2000021999701858e-06 }, "TrainerController._save_models": { "total": 0.3497657999978401, "count": 1, "self": 0.0943046000029426, "children": { "RLTrainer._checkpoint": { "total": 0.25546119999489747, "count": 1, "self": 0.25546119999489747 } } } } } } }