{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.908454179763794, "min": 1.8363007307052612, "max": 3.2957382202148438, "count": 531 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36459.109375, "min": 32417.89453125, "max": 105463.53125, "count": 531 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 64.34210526315789, "min": 43.8, "max": 999.0, "count": 531 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19560.0, "min": 12280.0, "max": 29736.0, "count": 531 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1522.2157075645775, "min": 1196.910318198774, "max": 1544.696067622339, "count": 517 }, "SoccerTwos.Self-play.ELO.sum": { "value": 231376.78754981578, "min": 2393.820636397548, "max": 332885.77805541456, "count": 517 }, "SoccerTwos.Step.mean": { "value": 5309995.0, "min": 9884.0, "max": 5309995.0, "count": 531 }, "SoccerTwos.Step.sum": { "value": 5309995.0, "min": 9884.0, "max": 5309995.0, "count": 531 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02603938803076744, "min": -0.09834785014390945, "max": 0.17717738449573517, "count": 531 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.9840264320373535, "min": -20.06296157836914, "max": 33.71331024169922, "count": 531 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0259746965020895, "min": -0.09736151993274689, "max": 0.18032267689704895, "count": 531 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.974128484725952, "min": -19.86174964904785, "max": 32.8303337097168, "count": 531 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 531 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 531 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.011599998068965339, "min": -0.6358181807127866, "max": 0.429154840207869, "count": 531 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.7747997045516968, "min": -63.53119999170303, "max": 63.98800003528595, "count": 531 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.011599998068965339, "min": -0.6358181807127866, "max": 0.429154840207869, "count": 531 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.7747997045516968, "min": -63.53119999170303, "max": 63.98800003528595, "count": 531 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 531 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 531 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019649455085163935, "min": 0.011493390523052463, "max": 0.02476633164236167, "count": 255 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019649455085163935, "min": 0.011493390523052463, "max": 0.02476633164236167, "count": 255 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08998010357220967, "min": 0.00010784915951565684, "max": 0.12197891374429067, "count": 255 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08998010357220967, "min": 0.00010784915951565684, "max": 0.12197891374429067, "count": 255 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0911549801627795, "min": 0.00011038151060347446, "max": 0.12372083142399788, "count": 255 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0911549801627795, "min": 0.00011038151060347446, "max": 0.12372083142399788, "count": 255 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 255 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 255 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 255 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 255 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 255 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 255 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682677729", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\lizar\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1682691180" }, "total": 13451.233284099999, "count": 1, "self": 0.7131810999999288, "children": { "run_training.setup": { "total": 0.16384220000000038, "count": 1, "self": 0.16384220000000038 }, "TrainerController.start_learning": { "total": 13450.3562608, "count": 1, "self": 9.277479199865411, "children": { "TrainerController._reset_env": { "total": 19.27394289999698, "count": 27, "self": 19.27394289999698 }, "TrainerController.advance": { "total": 13421.588028700136, "count": 363247, "self": 9.4548415009358, "children": { "env_step": { "total": 9262.102363599575, "count": 363247, "self": 5766.930768499857, "children": { "SubprocessEnvManager._take_step": { "total": 3489.256359299789, "count": 363247, "self": 58.64989790012942, "children": { "TorchPolicy.evaluate": { "total": 3430.6064613996596, "count": 670112, "self": 3430.6064613996596 } } }, "workers": { "total": 5.915235799929366, "count": 363247, "self": 0.0, "children": { "worker_root": { "total": 13425.940619100213, "count": 363247, "is_parallel": true, "self": 8729.450505800432, "children": { "steps_from_proto": { "total": 0.05567749999946159, "count": 54, "is_parallel": true, "self": 0.009588699998399619, "children": { "_process_rank_one_or_two_observation": { "total": 0.04608880000106197, "count": 216, "is_parallel": true, "self": 0.04608880000106197 } } }, "UnityEnvironment.step": { "total": 4696.43443579978, "count": 363247, "is_parallel": true, "self": 235.10029879948434, "children": { "UnityEnvironment._generate_step_input": { "total": 185.61395299970727, "count": 363247, "is_parallel": true, "self": 185.61395299970727 }, "communicator.exchange": { "total": 3519.033806199922, "count": 363247, "is_parallel": true, "self": 3519.033806199922 }, "steps_from_proto": { "total": 756.6863778006666, "count": 726494, "is_parallel": true, "self": 152.38173459970687, "children": { "_process_rank_one_or_two_observation": { "total": 604.3046432009597, "count": 2905976, "is_parallel": true, "self": 604.3046432009597 } } } } } } } } } } }, "trainer_advance": { "total": 4150.030823599625, "count": 363247, "self": 58.624215699388515, "children": { "process_trajectory": { "total": 1702.5560127002313, "count": 363247, "self": 1699.2910673002295, "children": { "RLTrainer._checkpoint": { "total": 3.2649454000018068, "count": 10, "self": 3.2649454000018068 } } }, "_update_policy": { "total": 2388.8505952000055, "count": 256, "self": 1035.7070891999701, "children": { "TorchPOCAOptimizer.update": { "total": 1353.1435060000354, "count": 7656, "self": 1353.1435060000354 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.21680899999955727, "count": 1, "self": 0.0068823999990854645, "children": { "RLTrainer._checkpoint": { "total": 0.2099266000004718, "count": 1, "self": 0.2099266000004718 } } } } } } }