{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7245991230010986, "min": 1.6280959844589233, "max": 1.803169846534729, "count": 690 }, "SoccerTwos.Policy.Entropy.sum": { "value": 34050.484375, "min": 16252.23046875, "max": 41848.55078125, "count": 690 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.42028985507247, "min": 41.73728813559322, "max": 107.25, "count": 690 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19988.0, "min": 7296.0, "max": 21240.0, "count": 690 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1652.446273309946, "min": 1623.0626194903318, "max": 1693.4569155917834, "count": 690 }, "SoccerTwos.Self-play.ELO.sum": { "value": 228037.58571677256, "min": 114220.06391457033, "max": 392609.14351578726, "count": 690 }, "SoccerTwos.Step.mean": { "value": 24009948.0, "min": 17119989.0, "max": 24009948.0, "count": 690 }, "SoccerTwos.Step.sum": { "value": 24009948.0, "min": 17119989.0, "max": 24009948.0, "count": 690 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03957207128405571, "min": -0.12997280061244965, "max": 0.07670627534389496, "count": 690 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.381801605224609, "min": -20.535701751708984, "max": 13.755611419677734, "count": 690 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03876207023859024, "min": -0.1288316398859024, "max": 0.07834520936012268, "count": 690 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.271641731262207, "min": -20.355398178100586, "max": 13.634573936462402, "count": 690 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 690 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 690 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.046152938814724195, "min": -0.36934179067611694, "max": 0.3203398482243818, "count": 690 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.27679967880249, "min": -62.43619990348816, "max": 46.91000020503998, "count": 690 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.046152938814724195, "min": -0.36934179067611694, "max": 0.3203398482243818, "count": 690 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.27679967880249, "min": -62.43619990348816, "max": 46.91000020503998, "count": 690 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 690 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 690 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014841787061747406, "min": 0.011989216684984665, "max": 0.023097134284519902, "count": 334 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014841787061747406, "min": 0.011989216684984665, "max": 0.023097134284519902, "count": 334 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10486778641740481, "min": 0.08783568665385247, "max": 0.13843777825435002, "count": 334 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10486778641740481, "min": 0.08783568665385247, "max": 0.13843777825435002, "count": 334 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1062960721552372, "min": 0.08942758962512017, "max": 0.14068217327197394, "count": 334 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1062960721552372, "min": 0.08942758962512017, "max": 0.14068217327197394, "count": 334 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 334 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 334 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 334 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 334 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.006000000000000002, "min": 0.006000000000000002, "max": 0.006000000000000002, "count": 334 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.006000000000000002, "min": 0.006000000000000002, "max": 0.006000000000000002, "count": 334 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688309449", "python_version": "3.9.16 (main, May 17 2023, 17:49:16) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\pepe\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1688336916" }, "total": 27466.885090400003, "count": 1, "self": 1.1405648000036308, "children": { "run_training.setup": { "total": 0.14519139999999986, "count": 1, "self": 0.14519139999999986 }, "TrainerController.start_learning": { "total": 27465.5993342, "count": 1, "self": 11.204596699637477, "children": { "TrainerController._reset_env": { "total": 9.80414069999125, "count": 36, "self": 9.80414069999125 }, "TrainerController.advance": { "total": 27444.38761920037, "count": 476298, "self": 11.01459670057011, "children": { "env_step": { "total": 7679.875852500507, "count": 476298, "self": 5911.034287698587, "children": { "SubprocessEnvManager._take_step": { "total": 1761.6579132017594, "count": 476298, "self": 67.78359530101602, "children": { "TorchPolicy.evaluate": { "total": 1693.8743179007433, "count": 865678, "self": 1693.8743179007433 } } }, "workers": { "total": 7.183651600160358, "count": 476297, "self": 0.0, "children": { "worker_root": { "total": 27439.14209659975, "count": 476297, "is_parallel": true, "self": 22733.734255899493, "children": { "steps_from_proto": { "total": 0.06647450001096544, "count": 72, "is_parallel": true, "self": 0.014102900009500985, "children": { "_process_rank_one_or_two_observation": { "total": 0.05237160000146446, "count": 288, "is_parallel": true, "self": 0.05237160000146446 } } }, "UnityEnvironment.step": { "total": 4705.341366200246, "count": 476297, "is_parallel": true, "self": 237.28460120103773, "children": { "UnityEnvironment._generate_step_input": { "total": 193.13705809924238, "count": 476297, "is_parallel": true, "self": 193.13705809924238 }, "communicator.exchange": { "total": 3466.292329999416, "count": 476297, "is_parallel": true, "self": 3466.292329999416 }, "steps_from_proto": { "total": 808.62737690055, "count": 952594, "is_parallel": true, "self": 167.28985730025352, "children": { "_process_rank_one_or_two_observation": { "total": 641.3375196002964, "count": 3810376, "is_parallel": true, "self": 641.3375196002964 } } } } } } } } } } }, "trainer_advance": { "total": 19753.497169999293, "count": 476297, "self": 87.17292039913082, "children": { "process_trajectory": { "total": 2177.9227992001324, "count": 476297, "self": 2175.370412100131, "children": { "RLTrainer._checkpoint": { "total": 2.5523871000011695, "count": 14, "self": 2.5523871000011695 } } }, "_update_policy": { "total": 17488.40145040003, "count": 335, "self": 1199.457120199988, "children": { "TorchPOCAOptimizer.update": { "total": 16288.944330200042, "count": 10050, "self": 16288.944330200042 } } } } } } }, "trainer_threads": { "total": 1.2000018614344299e-06, "count": 1, "self": 1.2000018614344299e-06 }, "TrainerController._save_models": { "total": 0.2029763999998977, "count": 1, "self": 0.06067310000071302, "children": { "RLTrainer._checkpoint": { "total": 0.14230329999918467, "count": 1, "self": 0.14230329999918467 } } } } } } }