{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.23771071434021, "min": 3.23771071434021, "max": 3.295820713043213, "count": 26 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28491.853515625, "min": 8391.232421875, "max": 52733.12890625, "count": 26 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 714.0, "min": 191.66666666666666, "max": 999.0, "count": 26 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 8568.0, "min": 2204.0, "max": 22100.0, "count": 26 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1001.8291290461129, "min": 1000.1956409054587, "max": 1005.3472247237237, "count": 23 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4007.3165161844518, "min": 2000.3912818109175, "max": 10038.79575043783, "count": 23 }, "SoccerTwos.Step.mean": { "value": 129996.0, "min": 4656.0, "max": 129996.0, "count": 26 }, "SoccerTwos.Step.sum": { "value": 129996.0, "min": 4656.0, "max": 129996.0, "count": 26 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04069586843252182, "min": -0.103403240442276, "max": -0.03872303664684296, "count": 26 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.48835042119026184, "min": -1.34423828125, "max": -0.4259534180164337, "count": 26 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04016890004277229, "min": -0.10340321063995361, "max": -0.03828540816903114, "count": 26 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4820268154144287, "min": -1.3442367315292358, "max": -0.4211394786834717, "count": 26 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 26 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 26 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.10442667206128438, "min": -0.800000011920929, "max": 0.6459733744462332, "count": 26 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.6265600323677063, "min": -3.686400055885315, "max": 3.8758402466773987, "count": 26 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1305333375930786, "min": -1.0, "max": 0.8074666857719421, "count": 26 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.7832000255584717, "min": -4.608000040054321, "max": 4.844800114631653, "count": 26 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014766910806065426, "min": 0.013285189863139143, "max": 0.02072374345593606, "count": 6 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014766910806065426, "min": 0.013285189863139143, "max": 0.02072374345593606, "count": 6 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0021963658082919816, "min": 0.0018074257849630985, "max": 0.005299923840599755, "count": 6 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0021963658082919816, "min": 0.0018074257849630985, "max": 0.005299923840599755, "count": 6 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0022314870613627134, "min": 0.0018156477934539769, "max": 0.00535708706981192, "count": 6 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0022314870613627134, "min": 0.0018156477934539769, "max": 0.00535708706981192, "count": 6 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00029610012129996, "min": 0.00029610012129996, "max": 0.0002993284802238399, "count": 6 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00029610012129996, "min": 0.00029610012129996, "max": 0.0002993284802238399, "count": 6 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19870004000000005, "min": 0.19870004000000005, "max": 0.19977615999999998, "count": 6 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19870004000000005, "min": 0.19870004000000005, "max": 0.19977615999999998, "count": 6 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.004935131995999999, "min": 0.004935131995999999, "max": 0.004988830384, "count": 6 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.004935131995999999, "min": 0.004935131995999999, "max": 0.004988830384, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717155959", "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": "\\\\?\\D:\\Programs\\Anaconda3\\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": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717156185" }, "total": 225.87608079996426, "count": 1, "self": 0.07468920003157109, "children": { "run_training.setup": { "total": 0.05783429997973144, "count": 1, "self": 0.05783429997973144 }, "TrainerController.start_learning": { "total": 225.74355729995295, "count": 1, "self": 0.16198030044324696, "children": { "TrainerController._reset_env": { "total": 4.075251600006595, "count": 2, "self": 4.075251600006595 }, "TrainerController.advance": { "total": 221.3517819995177, "count": 8620, "self": 0.16290820704307407, "children": { "env_step": { "total": 121.70785399532178, "count": 8620, "self": 93.73711119842483, "children": { "SubprocessEnvManager._take_step": { "total": 27.8769966987893, "count": 8620, "self": 0.9701793987769634, "children": { "TorchPolicy.evaluate": { "total": 26.906817300012335, "count": 17146, "self": 26.906817300012335 } } }, "workers": { "total": 0.09374609810765833, "count": 8620, "self": 0.0, "children": { "worker_root": { "total": 216.00840789743233, "count": 8620, "is_parallel": true, "self": 142.3634933962021, "children": { "steps_from_proto": { "total": 0.0038374000578187406, "count": 4, "is_parallel": true, "self": 0.0009646000689826906, "children": { "_process_rank_one_or_two_observation": { "total": 0.00287279998883605, "count": 16, "is_parallel": true, "self": 0.00287279998883605 } } }, "UnityEnvironment.step": { "total": 73.64107710117241, "count": 8620, "is_parallel": true, "self": 3.624384798342362, "children": { "UnityEnvironment._generate_step_input": { "total": 3.1010047000600025, "count": 8620, "is_parallel": true, "self": 3.1010047000600025 }, "communicator.exchange": { "total": 55.706702996685635, "count": 8620, "is_parallel": true, "self": 55.706702996685635 }, "steps_from_proto": { "total": 11.208984606084414, "count": 17240, "is_parallel": true, "self": 2.290967408567667, "children": { "_process_rank_one_or_two_observation": { "total": 8.918017197516747, "count": 68960, "is_parallel": true, "self": 8.918017197516747 } } } } } } } } } } }, "trainer_advance": { "total": 99.48101979715284, "count": 8620, "self": 1.4096503957989626, "children": { "process_trajectory": { "total": 20.840155201149173, "count": 8620, "self": 20.840155201149173 }, "_update_policy": { "total": 77.2312142002047, "count": 6, "self": 18.673083499947097, "children": { "TorchPOCAOptimizer.update": { "total": 58.55813070025761, "count": 183, "self": 58.55813070025761 } } } } } } }, "trainer_threads": { "total": 9.999494068324566e-07, "count": 1, "self": 9.999494068324566e-07 }, "TrainerController._save_models": { "total": 0.15454240003600717, "count": 1, "self": 0.002673500042874366, "children": { "RLTrainer._checkpoint": { "total": 0.1518688999931328, "count": 1, "self": 0.1518688999931328 } } } } } } }