{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.16239857673645, "min": 3.1376826763153076, "max": 3.2957229614257812, "count": 200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 54949.8359375, "min": 27747.2109375, "max": 134551.328125, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 989.0, "min": 469.1818181818182, "max": 999.0, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19780.0, "min": 10180.0, "max": 30024.0, "count": 200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1192.7689399002395, "min": 1191.3316353552425, "max": 1205.8818748200704, "count": 134 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2385.537879800479, "min": 2384.9632572446317, "max": 16719.50558842189, "count": 134 }, "SoccerTwos.Step.mean": { "value": 1999434.0, "min": 9028.0, "max": 1999434.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 1999434.0, "min": 9028.0, "max": 1999434.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0011798698687925935, "min": -0.02502206340432167, "max": 0.08962079137563705, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.011798698455095291, "min": -0.3106764256954193, "max": 1.3442800045013428, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.001204676111228764, "min": -0.02149164117872715, "max": 0.08961851894855499, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.012046760879456997, "min": -0.3381226658821106, "max": 1.3442559242248535, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.010040000081062317, "min": -0.5833333333333334, "max": 0.397800001833174, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.10040000081062317, "min": -7.0, "max": 7.160400032997131, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.010040000081062317, "min": -0.5833333333333334, "max": 0.397800001833174, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.10040000081062317, "min": -7.0, "max": 7.160400032997131, "count": 200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01955348037008662, "min": 0.011535956555356582, "max": 0.024529908857463548, "count": 92 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01955348037008662, "min": 0.011535956555356582, "max": 0.024529908857463548, "count": 92 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.0319110338580987e-06, "min": 1.0245982423384702e-06, "max": 0.005152893213865657, "count": 92 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.0319110338580987e-06, "min": 1.0245982423384702e-06, "max": 0.005152893213865657, "count": 92 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 2.7254537750801926e-06, "min": 1.3955561219821296e-06, "max": 0.005246324775119622, "count": 92 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 2.7254537750801926e-06, "min": 1.3955561219821296e-06, "max": 0.005246324775119622, "count": 92 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 92 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 92 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 92 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 92 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 92 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 92 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675645778", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\hecto\\.conda\\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": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675659901" }, "total": 14123.837236899999, "count": 1, "self": 0.2208240999989357, "children": { "run_training.setup": { "total": 0.07280140000000013, "count": 1, "self": 0.07280140000000013 }, "TrainerController.start_learning": { "total": 14123.5436114, "count": 1, "self": 2.3255299998345436, "children": { "TrainerController._reset_env": { "total": 2.6708188999974034, "count": 10, "self": 2.6708188999974034 }, "TrainerController.advance": { "total": 14118.448119400166, "count": 130277, "self": 2.4540254002531583, "children": { "env_step": { "total": 1840.837251199772, "count": 130277, "self": 1420.94400949985, "children": { "SubprocessEnvManager._take_step": { "total": 418.30428439979727, "count": 130277, "self": 14.27456359988065, "children": { "TorchPolicy.evaluate": { "total": 404.0297207999166, "count": 258728, "self": 404.0297207999166 } } }, "workers": { "total": 1.5889573001248922, "count": 130277, "self": 0.0, "children": { "worker_root": { "total": 14117.761179999885, "count": 130277, "is_parallel": true, "self": 12984.705145900174, "children": { "steps_from_proto": { "total": 0.012056800004279555, "count": 20, "is_parallel": true, "self": 0.0024622000184950643, "children": { "_process_rank_one_or_two_observation": { "total": 0.009594599985784491, "count": 80, "is_parallel": true, "self": 0.009594599985784491 } } }, "UnityEnvironment.step": { "total": 1133.0439772997056, "count": 130277, "is_parallel": true, "self": 56.620880199013754, "children": { "UnityEnvironment._generate_step_input": { "total": 54.34628549967154, "count": 130277, "is_parallel": true, "self": 54.34628549967154 }, "communicator.exchange": { "total": 865.5779003000882, "count": 130277, "is_parallel": true, "self": 865.5779003000882 }, "steps_from_proto": { "total": 156.49891130093215, "count": 260554, "is_parallel": true, "self": 31.378073299472632, "children": { "_process_rank_one_or_two_observation": { "total": 125.12083800145952, "count": 1042216, "is_parallel": true, "self": 125.12083800145952 } } } } } } } } } } }, "trainer_advance": { "total": 12275.156842800141, "count": 130277, "self": 18.854514199558253, "children": { "process_trajectory": { "total": 9984.574335500576, "count": 130277, "self": 9984.165171000575, "children": { "RLTrainer._checkpoint": { "total": 0.4091645000007702, "count": 4, "self": 0.4091645000007702 } } }, "_update_policy": { "total": 2271.7279931000066, "count": 92, "self": 256.19466130005685, "children": { "TorchPOCAOptimizer.update": { "total": 2015.5333317999498, "count": 2769, "self": 2015.5333317999498 } } } } } } }, "trainer_threads": { "total": 6.000009307172149e-07, "count": 1, "self": 6.000009307172149e-07 }, "TrainerController._save_models": { "total": 0.09914250000110769, "count": 1, "self": 0.006318500001725624, "children": { "RLTrainer._checkpoint": { "total": 0.09282399999938207, "count": 1, "self": 0.09282399999938207 } } } } } } }