{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.9886515140533447, "min": 2.8776695728302, "max": 3.2957441806793213, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 77083.296875, "min": 21003.193359375, "max": 143326.15625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 348.14285714285717, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 13740.0, "max": 28680.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1164.848985779112, "min": 1164.5178833728528, "max": 1199.6461445698528, "count": 253 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2329.697971558224, "min": 2329.678079995595, "max": 21226.461981190987, "count": 253 }, "SoccerTwos.Step.mean": { "value": 4999488.0, "min": 9358.0, "max": 4999488.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999488.0, "min": 9358.0, "max": 4999488.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0003431244404055178, "min": -0.028341375291347504, "max": 0.0887782946228981, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.0034312442876398563, "min": -0.42512062191963196, "max": 1.1541178226470947, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0003485643828753382, "min": -0.028018254786729813, "max": 0.0887521505355835, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.003485643770545721, "min": -0.4202738106250763, "max": 1.1537779569625854, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.631578947368421, "max": 0.44071110751893783, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -12.0, "max": 7.932799935340881, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.631578947368421, "max": 0.44071110751893783, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -12.0, "max": 7.932799935340881, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.0167025576151597, "min": 0.01178024789793805, "max": 0.023278041661251338, "count": 231 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0167025576151597, "min": 0.01178024789793805, "max": 0.023278041661251338, "count": 231 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 1.2005250620283903e-06, "min": 6.482456615941601e-09, "max": 0.007855950311447183, "count": 231 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 1.2005250620283903e-06, "min": 6.482456615941601e-09, "max": 0.007855950311447183, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 1.2068932861393952e-06, "min": 7.715949938239911e-09, "max": 0.007875663150722781, "count": 231 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 1.2068932861393952e-06, "min": 7.715949938239911e-09, "max": 0.007875663150722781, "count": 231 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 231 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 231 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 231 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707287606", "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\\ramsi\\anaconda3\\envs\\hfrl\\Scripts\\mlagents-learn C:\\Users\\ramsi\\OneDrive\\Documents\\Github Projects\\reinforcement-learning\\HuggingFace-RLCourse\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=C:\\Users\\ramsi\\OneDrive\\Documents\\Github Projects\\reinforcement-learning\\HuggingFace-RLCourse\\ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1707296319" }, "total": 8713.064709100057, "count": 1, "self": 2.027184100006707, "children": { "run_training.setup": { "total": 0.09109230001922697, "count": 1, "self": 0.09109230001922697 }, "TrainerController.start_learning": { "total": 8710.946432700031, "count": 1, "self": 5.462006586720236, "children": { "TrainerController._reset_env": { "total": 6.314539300277829, "count": 25, "self": 6.314539300277829 }, "TrainerController.advance": { "total": 8699.040651713032, "count": 326185, "self": 5.753925517317839, "children": { "env_step": { "total": 4144.400120237493, "count": 326185, "self": 3197.684009380988, "children": { "SubprocessEnvManager._take_step": { "total": 943.1199036971666, "count": 326185, "self": 35.2558862764854, "children": { "TorchPolicy.evaluate": { "total": 907.8640174206812, "count": 647666, "self": 907.8640174206812 } } }, "workers": { "total": 3.596207159338519, "count": 326185, "self": 0.0, "children": { "worker_root": { "total": 8698.748673381284, "count": 326185, "is_parallel": true, "self": 6164.275183456251, "children": { "steps_from_proto": { "total": 0.03010450000874698, "count": 50, "is_parallel": true, "self": 0.006091700633987784, "children": { "_process_rank_one_or_two_observation": { "total": 0.024012799374759197, "count": 200, "is_parallel": true, "self": 0.024012799374759197 } } }, "UnityEnvironment.step": { "total": 2534.4433854250237, "count": 326185, "is_parallel": true, "self": 118.31500989513006, "children": { "UnityEnvironment._generate_step_input": { "total": 86.19965206331108, "count": 326185, "is_parallel": true, "self": 86.19965206331108 }, "communicator.exchange": { "total": 1954.621456268127, "count": 326185, "is_parallel": true, "self": 1954.621456268127 }, "steps_from_proto": { "total": 375.3072671984555, "count": 652370, "is_parallel": true, "self": 74.32913937082049, "children": { "_process_rank_one_or_two_observation": { "total": 300.97812782763503, "count": 2609480, "is_parallel": true, "self": 300.97812782763503 } } } } } } } } } } }, "trainer_advance": { "total": 4548.8866059582215, "count": 326185, "self": 44.64638174988795, "children": { "process_trajectory": { "total": 624.5394466089783, "count": 326185, "self": 623.4968685091008, "children": { "RLTrainer._checkpoint": { "total": 1.0425780998775735, "count": 10, "self": 1.0425780998775735 } } }, "_update_policy": { "total": 3879.700777599355, "count": 231, "self": 513.9343299011234, "children": { "TorchPOCAOptimizer.update": { "total": 3365.766447698232, "count": 6930, "self": 3365.766447698232 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.12923419999424368, "count": 1, "self": 0.013538599945604801, "children": { "RLTrainer._checkpoint": { "total": 0.11569560004863888, "count": 1, "self": 0.11569560004863888 } } } } } } }