{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1884450912475586, "min": 3.1543173789978027, "max": 3.295722007751465, "count": 100 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44383.15625, "min": 5364.7880859375, "max": 105463.1015625, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 918.4, "min": 393.54545454545456, "max": 999.0, "count": 100 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18368.0, "min": 3996.0, "max": 28172.0, "count": 100 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1208.8509585019856, "min": 1194.0402364530805, "max": 1212.045870328748, "count": 81 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2417.701917003971, "min": 2388.080472906161, "max": 14481.386916658726, "count": 81 }, "SoccerTwos.Step.mean": { "value": 999252.0, "min": 9062.0, "max": 999252.0, "count": 100 }, "SoccerTwos.Step.sum": { "value": 999252.0, "min": 9062.0, "max": 999252.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.010445845313370228, "min": -0.07581650465726852, "max": 0.019616320729255676, "count": 100 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.11490429937839508, "min": -0.9097980856895447, "max": 0.23539584875106812, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.010502335615456104, "min": -0.07582205533981323, "max": 0.019769296050071716, "count": 100 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.11552569270133972, "min": -0.9098646640777588, "max": 0.2372315526008606, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07312727516347711, "min": -0.41153333336114883, "max": 0.36257500760257244, "count": 100 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.8044000267982483, "min": -6.468800067901611, "max": 5.801200121641159, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07312727516347711, "min": -0.41153333336114883, "max": 0.36257500760257244, "count": 100 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.8044000267982483, "min": -6.468800067901611, "max": 5.801200121641159, "count": 100 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015264107022327758, "min": 0.012924301449675112, "max": 0.023621039185672998, "count": 46 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015264107022327758, "min": 0.012924301449675112, "max": 0.023621039185672998, "count": 46 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0012293039365128303, "min": 4.021294789708918e-05, "max": 0.005852521955966949, "count": 46 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0012293039365128303, "min": 4.021294789708918e-05, "max": 0.005852521955966949, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0012328454526141287, "min": 3.709641429547143e-05, "max": 0.006051869333411257, "count": 46 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0012328454526141287, "min": 3.709641429547143e-05, "max": 0.006051869333411257, "count": 46 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 46 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 46 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 46 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684797705", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Alfin\\.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": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1684800727" }, "total": 3021.412926, "count": 1, "self": 0.17689329999984693, "children": { "run_training.setup": { "total": 0.052013899999999946, "count": 1, "self": 0.052013899999999946 }, "TrainerController.start_learning": { "total": 3021.1840188, "count": 1, "self": 2.0456582000333583, "children": { "TrainerController._reset_env": { "total": 3.076991899999862, "count": 10, "self": 3.076991899999862 }, "TrainerController.advance": { "total": 3015.9242281999673, "count": 67283, "self": 2.1239989999580757, "children": { "env_step": { "total": 1503.0990195000438, "count": 67283, "self": 1055.9908713999403, "children": { "SubprocessEnvManager._take_step": { "total": 445.81550570008653, "count": 67283, "self": 13.244350500097084, "children": { "TorchPolicy.evaluate": { "total": 432.57115519998945, "count": 133582, "self": 432.57115519998945 } } }, "workers": { "total": 1.2926424000169146, "count": 67283, "self": 0.0, "children": { "worker_root": { "total": 3014.9546084999756, "count": 67283, "is_parallel": true, "self": 2221.3383639999324, "children": { "steps_from_proto": { "total": 0.03136619999971435, "count": 20, "is_parallel": true, "self": 0.004794099998373547, "children": { "_process_rank_one_or_two_observation": { "total": 0.026572100001340804, "count": 80, "is_parallel": true, "self": 0.026572100001340804 } } }, "UnityEnvironment.step": { "total": 793.5848783000436, "count": 67283, "is_parallel": true, "self": 44.424546500087786, "children": { "UnityEnvironment._generate_step_input": { "total": 52.24842179995653, "count": 67283, "is_parallel": true, "self": 52.24842179995653 }, "communicator.exchange": { "total": 542.3120904000126, "count": 67283, "is_parallel": true, "self": 542.3120904000126 }, "steps_from_proto": { "total": 154.5998195999866, "count": 134566, "is_parallel": true, "self": 34.44958509982793, "children": { "_process_rank_one_or_two_observation": { "total": 120.15023450015867, "count": 538264, "is_parallel": true, "self": 120.15023450015867 } } } } } } } } } } }, "trainer_advance": { "total": 1510.7012096999651, "count": 67283, "self": 12.211857299984786, "children": { "process_trajectory": { "total": 241.55741609998103, "count": 67283, "self": 240.38777189998126, "children": { "RLTrainer._checkpoint": { "total": 1.169644199999766, "count": 2, "self": 1.169644199999766 } } }, "_update_policy": { "total": 1256.9319362999993, "count": 46, "self": 152.37882540000396, "children": { "TorchPOCAOptimizer.update": { "total": 1104.5531108999953, "count": 1389, "self": 1104.5531108999953 } } } } } } }, "trainer_threads": { "total": 9.99999883788405e-07, "count": 1, "self": 9.99999883788405e-07 }, "TrainerController._save_models": { "total": 0.13713949999964825, "count": 1, "self": 0.020320199999332544, "children": { "RLTrainer._checkpoint": { "total": 0.1168193000003157, "count": 1, "self": 0.1168193000003157 } } } } } } }