{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6343201398849487, "min": 1.63372004032135, "max": 3.295745849609375, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30751.3671875, "min": 19058.6640625, "max": 110315.203125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.13186813186813, "min": 39.60504201680672, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19704.0, "min": 17408.0, "max": 23628.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1630.8173965114254, "min": 1200.5430052443305, "max": 1661.5012614088787, "count": 495 }, "SoccerTwos.Self-play.ELO.sum": { "value": 296808.76616507943, "min": 2405.555724286956, "max": 392532.59903059853, "count": 495 }, "SoccerTwos.Step.mean": { "value": 4999933.0, "min": 9834.0, "max": 4999933.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999933.0, "min": 9834.0, "max": 4999933.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06500574946403503, "min": -0.11678871512413025, "max": 0.2105601578950882, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -11.831047058105469, "min": -19.499401092529297, "max": 32.84738540649414, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07573764026165009, "min": -0.12424995750188828, "max": 0.2139291912317276, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -13.784250259399414, "min": -20.54096221923828, "max": 32.99591827392578, "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": -0.09392417426947709, "min": -0.46277036931779647, "max": 0.5204642862081528, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -17.09419971704483, "min": -63.085399866104126, "max": 55.88759994506836, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09392417426947709, "min": -0.46277036931779647, "max": 0.5204642862081528, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -17.09419971704483, "min": -63.085399866104126, "max": 55.88759994506836, "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": 0.017769427599948054, "min": 0.010217673702087874, "max": 0.02355038944321374, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017769427599948054, "min": 0.010217673702087874, "max": 0.02355038944321374, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10117773289481799, "min": 0.00028914453481168796, "max": 0.12917149538795153, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10117773289481799, "min": 0.00028914453481168796, "max": 0.12917149538795153, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10313539529840152, "min": 0.0002874859002380011, "max": 0.13052500411868095, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10313539529840152, "min": 0.0002874859002380011, "max": 0.13052500411868095, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718344258", "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\\Lenovo\\.conda\\envs\\mlagent\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1718357779" }, "total": 13520.7158217, "count": 1, "self": 0.4479704999994283, "children": { "run_training.setup": { "total": 0.09344960000089486, "count": 1, "self": 0.09344960000089486 }, "TrainerController.start_learning": { "total": 13520.1744016, "count": 1, "self": 8.820788400895253, "children": { "TrainerController._reset_env": { "total": 5.112340000003314, "count": 25, "self": 5.112340000003314 }, "TrainerController.advance": { "total": 13506.130232099104, "count": 345164, "self": 8.592391099607994, "children": { "env_step": { "total": 5723.071923999429, "count": 345164, "self": 4373.200629699706, "children": { "SubprocessEnvManager._take_step": { "total": 1344.456311300104, "count": 345164, "self": 49.85553000071923, "children": { "TorchPolicy.evaluate": { "total": 1294.6007812993848, "count": 630162, "self": 1294.6007812993848 } } }, "workers": { "total": 5.414982999618587, "count": 345164, "self": 0.0, "children": { "worker_root": { "total": 13505.022121900205, "count": 345164, "is_parallel": true, "self": 10148.646386600243, "children": { "steps_from_proto": { "total": 0.043051000002378714, "count": 50, "is_parallel": true, "self": 0.008841700026096078, "children": { "_process_rank_one_or_two_observation": { "total": 0.03420929997628264, "count": 200, "is_parallel": true, "self": 0.03420929997628264 } } }, "UnityEnvironment.step": { "total": 3356.3326842999595, "count": 345164, "is_parallel": true, "self": 185.92534930002512, "children": { "UnityEnvironment._generate_step_input": { "total": 168.55699630026174, "count": 345164, "is_parallel": true, "self": 168.55699630026174 }, "communicator.exchange": { "total": 2405.0876991992372, "count": 345164, "is_parallel": true, "self": 2405.0876991992372 }, "steps_from_proto": { "total": 596.7626395004354, "count": 690328, "is_parallel": true, "self": 118.38028860218401, "children": { "_process_rank_one_or_two_observation": { "total": 478.3823508982514, "count": 2761312, "is_parallel": true, "self": 478.3823508982514 } } } } } } } } } } }, "trainer_advance": { "total": 7774.465917000067, "count": 345164, "self": 68.75999809924724, "children": { "process_trajectory": { "total": 1474.6640641008216, "count": 345164, "self": 1473.3064660008167, "children": { "RLTrainer._checkpoint": { "total": 1.3575981000049069, "count": 10, "self": 1.3575981000049069 } } }, "_update_policy": { "total": 6231.041854799998, "count": 241, "self": 815.0118631999139, "children": { "TorchPOCAOptimizer.update": { "total": 5416.029991600084, "count": 7230, "self": 5416.029991600084 } } } } } } }, "trainer_threads": { "total": 1.0999974620062858e-06, "count": 1, "self": 1.0999974620062858e-06 }, "TrainerController._save_models": { "total": 0.11103999999977532, "count": 1, "self": 0.0028047000014339574, "children": { "RLTrainer._checkpoint": { "total": 0.10823529999834136, "count": 1, "self": 0.10823529999834136 } } } } } } }