{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.625529170036316, "min": 1.539237380027771, "max": 3.2957592010498047, "count": 2690 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32926.71875, "min": 18381.7578125, "max": 154017.21875, "count": 2690 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.3, "min": 42.64912280701754, "max": 999.0, "count": 2690 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19684.0, "min": 14304.0, "max": 26064.0, "count": 2690 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1696.018945543951, "min": 1192.4075635790145, "max": 1708.100005648963, "count": 2629 }, "SoccerTwos.Self-play.ELO.sum": { "value": 237442.65237615316, "min": 2387.1815364120403, "max": 354667.5704776909, "count": 2629 }, "SoccerTwos.Step.mean": { "value": 26899986.0, "min": 9048.0, "max": 26899986.0, "count": 2690 }, "SoccerTwos.Step.sum": { "value": 26899986.0, "min": 9048.0, "max": 26899986.0, "count": 2690 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.07824275642633438, "min": -0.1242128387093544, "max": 0.15856412053108215, "count": 2690 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 10.953986167907715, "min": -19.395774841308594, "max": 21.93661880493164, "count": 2690 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0793059766292572, "min": -0.12276865541934967, "max": 0.15983742475509644, "count": 2690 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 11.102836608886719, "min": -19.94377899169922, "max": 22.69306182861328, "count": 2690 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2690 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2690 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.15907999788011823, "min": -0.7142857142857143, "max": 0.3968545447696339, "count": 2690 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 22.271199703216553, "min": -56.322800278663635, "max": 56.388400077819824, "count": 2690 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.15907999788011823, "min": -0.7142857142857143, "max": 0.3968545447696339, "count": 2690 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 22.271199703216553, "min": -56.322800278663635, "max": 56.388400077819824, "count": 2690 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2690 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2690 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01611374831603219, "min": 0.010568836365973767, "max": 0.024785814211160564, "count": 1299 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01611374831603219, "min": 0.010568836365973767, "max": 0.024785814211160564, "count": 1299 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09546585033337275, "min": 7.622673147504125e-07, "max": 0.12446315536896388, "count": 1299 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09546585033337275, "min": 7.622673147504125e-07, "max": 0.12446315536896388, "count": 1299 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09696782380342484, "min": 7.988116199915869e-07, "max": 0.12608572021126746, "count": 1299 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09696782380342484, "min": 7.988116199915869e-07, "max": 0.12608572021126746, "count": 1299 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1299 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1299 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1299 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1299 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1299 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1299 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717920335", "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\\lucam\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=D:\\Unicatt\\Deep_Learning_Applications\\ml-agents\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos_v1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717968387" }, "total": 48050.21504079999, "count": 1, "self": 0.26786449999781325, "children": { "run_training.setup": { "total": 0.07256979998783208, "count": 1, "self": 0.07256979998783208 }, "TrainerController.start_learning": { "total": 48049.8746065, "count": 1, "self": 32.64125469879946, "children": { "TrainerController._reset_env": { "total": 7.581888800021261, "count": 135, "self": 7.581888800021261 }, "TrainerController.advance": { "total": 48009.55168560118, "count": 1839481, "self": 30.097768619307317, "children": { "env_step": { "total": 20641.777884882235, "count": 1839481, "self": 15718.422649371641, "children": { "SubprocessEnvManager._take_step": { "total": 4903.580488634587, "count": 1839481, "self": 191.70478327095043, "children": { "TorchPolicy.evaluate": { "total": 4711.875705363636, "count": 3390310, "self": 4711.875705363636 } } }, "workers": { "total": 19.774746876006247, "count": 1839481, "self": 0.0, "children": { "worker_root": { "total": 47995.45239857878, "count": 1839481, "is_parallel": true, "self": 35693.16901127933, "children": { "steps_from_proto": { "total": 0.1437859999423381, "count": 270, "is_parallel": true, "self": 0.030283999862149358, "children": { "_process_rank_one_or_two_observation": { "total": 0.11350200008018874, "count": 1080, "is_parallel": true, "self": 0.11350200008018874 } } }, "UnityEnvironment.step": { "total": 12302.13960129951, "count": 1839481, "is_parallel": true, "self": 574.4306377614266, "children": { "UnityEnvironment._generate_step_input": { "total": 468.0131852145714, "count": 1839481, "is_parallel": true, "self": 468.0131852145714 }, "communicator.exchange": { "total": 9457.475427884172, "count": 1839481, "is_parallel": true, "self": 9457.475427884172 }, "steps_from_proto": { "total": 1802.22035043934, "count": 3678962, "is_parallel": true, "self": 379.59120696550235, "children": { "_process_rank_one_or_two_observation": { "total": 1422.6291434738378, "count": 14715848, "is_parallel": true, "self": 1422.6291434738378 } } } } } } } } } } }, "trainer_advance": { "total": 27337.67603209964, "count": 1839481, "self": 271.3230778631987, "children": { "process_trajectory": { "total": 5412.732093736267, "count": 1839481, "self": 5407.888901736238, "children": { "RLTrainer._checkpoint": { "total": 4.843192000029376, "count": 53, "self": 4.843192000029376 } } }, "_update_policy": { "total": 21653.620860500174, "count": 1300, "self": 2673.0894467009057, "children": { "TorchPOCAOptimizer.update": { "total": 18980.53141379927, "count": 38981, "self": 18980.53141379927 } } } } } } }, "trainer_threads": { "total": 1.200009137392044e-06, "count": 1, "self": 1.200009137392044e-06 }, "TrainerController._save_models": { "total": 0.09977619998971932, "count": 1, "self": 0.0027324999682605267, "children": { "RLTrainer._checkpoint": { "total": 0.09704370002145879, "count": 1, "self": 0.09704370002145879 } } } } } } }