{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.6636552810668945, "min": 2.639509439468384, "max": 3.2957053184509277, "count": 183 }, "SoccerTwos.Policy.Entropy.sum": { "value": 50630.7578125, "min": 27222.552734375, "max": 105462.5546875, "count": 183 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.87142857142857, "min": 60.566265060240966, "max": 999.0, "count": 183 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19844.0, "min": 16712.0, "max": 25512.0, "count": 183 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1377.8216428057224, "min": 1194.0276339018535, "max": 1377.8216428057224, "count": 180 }, "SoccerTwos.Self-play.ELO.sum": { "value": 192895.02999280114, "min": 2388.203457608957, "max": 224915.3224771908, "count": 180 }, "SoccerTwos.Step.mean": { "value": 1829910.0, "min": 9776.0, "max": 1829910.0, "count": 183 }, "SoccerTwos.Step.sum": { "value": 1829910.0, "min": 9776.0, "max": 1829910.0, "count": 183 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06736195087432861, "min": -0.044009752571582794, "max": 0.18304480612277985, "count": 183 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 9.430673599243164, "min": -0.8046436905860901, "max": 19.386768341064453, "count": 183 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0787060335278511, "min": -0.043588925153017044, "max": 0.17826050519943237, "count": 183 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 11.018844604492188, "min": -1.2285666465759277, "max": 19.917972564697266, "count": 183 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 183 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 183 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05146285465785435, "min": -0.7533043467480204, "max": 0.47261176214498635, "count": 183 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 7.204799652099609, "min": -28.551200069487095, "max": 48.61659997701645, "count": 183 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05146285465785435, "min": -0.7533043467480204, "max": 0.47261176214498635, "count": 183 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 7.204799652099609, "min": -28.551200069487095, "max": 48.61659997701645, "count": 183 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 183 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 183 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014108828387300794, "min": 0.01203829750981337, "max": 0.025191979583663246, "count": 86 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014108828387300794, "min": 0.01203829750981337, "max": 0.025191979583663246, "count": 86 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0775225800772508, "min": 0.00011211502593747961, "max": 0.07754862308502197, "count": 86 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0775225800772508, "min": 0.00011211502593747961, "max": 0.07754862308502197, "count": 86 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07896504228313764, "min": 0.00010771451197797433, "max": 0.07896504228313764, "count": 86 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07896504228313764, "min": 0.00010771451197797433, "max": 0.07896504228313764, "count": 86 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 86 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 86 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 86 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 86 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 86 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 86 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700914945", "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\\yogna\\.conda\\envs\\rl\\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": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1700933587" }, "total": 18644.466503800002, "count": 1, "self": 1.7566883999897982, "children": { "run_training.setup": { "total": 0.1050355000043055, "count": 1, "self": 0.1050355000043055 }, "TrainerController.start_learning": { "total": 18642.604779900008, "count": 1, "self": 4.240188402960484, "children": { "TrainerController._reset_env": { "total": 4.652556699998968, "count": 8, "self": 4.652556699998968 }, "TrainerController.advance": { "total": 18633.43719849705, "count": 119350, "self": 4.290942599589471, "children": { "env_step": { "total": 3560.5795205981194, "count": 119350, "self": 2784.2127627998198, "children": { "SubprocessEnvManager._take_step": { "total": 773.5320777976958, "count": 119350, "self": 23.776223795633996, "children": { "TorchPolicy.evaluate": { "total": 749.7558540020618, "count": 231864, "self": 749.7558540020618 } } }, "workers": { "total": 2.8346800006038393, "count": 119349, "self": 0.0, "children": { "worker_root": { "total": 18632.299003496926, "count": 119349, "is_parallel": true, "self": 16403.130215300902, "children": { "steps_from_proto": { "total": 0.021072899988212157, "count": 16, "is_parallel": true, "self": 0.004751700005726889, "children": { "_process_rank_one_or_two_observation": { "total": 0.016321199982485268, "count": 64, "is_parallel": true, "self": 0.016321199982485268 } } }, "UnityEnvironment.step": { "total": 2229.147715296036, "count": 119349, "is_parallel": true, "self": 109.86077690042293, "children": { "UnityEnvironment._generate_step_input": { "total": 114.00625709873566, "count": 119349, "is_parallel": true, "self": 114.00625709873566 }, "communicator.exchange": { "total": 1629.412547401189, "count": 119349, "is_parallel": true, "self": 1629.412547401189 }, "steps_from_proto": { "total": 375.8681338956885, "count": 238698, "is_parallel": true, "self": 76.06153618592361, "children": { "_process_rank_one_or_two_observation": { "total": 299.8065977097649, "count": 954792, "is_parallel": true, "self": 299.8065977097649 } } } } } } } } } } }, "trainer_advance": { "total": 15068.56673529934, "count": 119349, "self": 28.789334897905064, "children": { "process_trajectory": { "total": 11446.739638101484, "count": 119349, "self": 11445.99410500149, "children": { "RLTrainer._checkpoint": { "total": 0.7455330999946455, "count": 3, "self": 0.7455330999946455 } } }, "_update_policy": { "total": 3593.0377622999513, "count": 86, "self": 341.1176911001385, "children": { "TorchPOCAOptimizer.update": { "total": 3251.920071199813, "count": 2580, "self": 3251.920071199813 } } } } } } }, "trainer_threads": { "total": 2.2000021999701858e-06, "count": 1, "self": 2.2000021999701858e-06 }, "TrainerController._save_models": { "total": 0.2748340999969514, "count": 1, "self": 0.019813199993222952, "children": { "RLTrainer._checkpoint": { "total": 0.25502090000372846, "count": 1, "self": 0.25502090000372846 } } } } } } }