{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4541367292404175, "min": 1.2375152111053467, "max": 3.1320574283599854, "count": 2149 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29641.123046875, "min": 22702.34765625, "max": 99956.203125, "count": 2149 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.23711340206186, "min": 39.57377049180328, "max": 999.0, "count": 2149 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19492.0, "min": 4992.0, "max": 23064.0, "count": 2149 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1690.3184599198976, "min": 1240.3301940147737, "max": 1717.6282291273603, "count": 2148 }, "SoccerTwos.Self-play.ELO.sum": { "value": 327921.7812244601, "min": 4978.456025288048, "max": 411136.9628038114, "count": 2148 }, "SoccerTwos.Step.mean": { "value": 25129952.0, "min": 3649775.0, "max": 25129952.0, "count": 2149 }, "SoccerTwos.Step.sum": { "value": 25129952.0, "min": 3649775.0, "max": 25129952.0, "count": 2149 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03563397377729416, "min": -0.14790469408035278, "max": 0.21847504377365112, "count": 2149 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.948624610900879, "min": -26.592159271240234, "max": 32.77125549316406, "count": 2149 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.030216647312045097, "min": -0.14879702031612396, "max": 0.22972778975963593, "count": 2149 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.892246246337891, "min": -28.268308639526367, "max": 34.45916748046875, "count": 2149 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2149 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2149 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1109282041207338, "min": -0.5572363625873219, "max": 0.5313407436565116, "count": 2149 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -21.63099980354309, "min": -61.24120008945465, "max": 59.0591995716095, "count": 2149 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1109282041207338, "min": -0.5572363625873219, "max": 0.5313407436565116, "count": 2149 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -21.63099980354309, "min": -61.24120008945465, "max": 59.0591995716095, "count": 2149 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2149 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2149 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.022764509086846373, "min": 0.009685336826563192, "max": 0.02565293670243894, "count": 1042 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.022764509086846373, "min": 0.009685336826563192, "max": 0.02565293670243894, "count": 1042 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12950191671649616, "min": 0.0033425594214349986, "max": 0.16743886222441992, "count": 1042 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12950191671649616, "min": 0.0033425594214349986, "max": 0.16743886222441992, "count": 1042 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1310691346724828, "min": 0.003399091570948561, "max": 0.1712032919128736, "count": 1042 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1310691346724828, "min": 0.003399091570948561, "max": 0.1712032919128736, "count": 1042 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1042 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1042 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1042 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1042 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1042 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1042 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701568682", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\P:\\envs\\rl\\Scripts\\mlagents-learn P:\\projects\\machine_learning_projects\\ai_vs_ai\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "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": "1701637341" }, "total": 68658.9599409, "count": 1, "self": 0.21699479999369942, "children": { "run_training.setup": { "total": 0.08193220000248402, "count": 1, "self": 0.08193220000248402 }, "TrainerController.start_learning": { "total": 68658.6610139, "count": 1, "self": 35.3683730938792, "children": { "TrainerController._reset_env": { "total": 5.628104999988864, "count": 109, "self": 5.628104999988864 }, "TrainerController.advance": { "total": 68617.53049780613, "count": 1495413, "self": 31.63212630386988, "children": { "env_step": { "total": 25251.367267200425, "count": 1495413, "self": 19903.576513396678, "children": { "SubprocessEnvManager._take_step": { "total": 5325.007258799444, "count": 1495413, "self": 179.27663200836832, "children": { "TorchPolicy.evaluate": { "total": 5145.730626791075, "count": 2697296, "self": 5145.730626791075 } } }, "workers": { "total": 22.783495004303404, "count": 1495413, "self": 0.0, "children": { "worker_root": { "total": 68601.84516440403, "count": 1495413, "is_parallel": true, "self": 52816.90971182069, "children": { "steps_from_proto": { "total": 0.1947636000768398, "count": 218, "is_parallel": true, "self": 0.03588760009006364, "children": { "_process_rank_one_or_two_observation": { "total": 0.15887599998677615, "count": 872, "is_parallel": true, "self": 0.15887599998677615 } } }, "UnityEnvironment.step": { "total": 15784.740688983264, "count": 1495413, "is_parallel": true, "self": 769.8504399854864, "children": { "UnityEnvironment._generate_step_input": { "total": 642.8728582056501, "count": 1495413, "is_parallel": true, "self": 642.8728582056501 }, "communicator.exchange": { "total": 11825.80669318459, "count": 1495413, "is_parallel": true, "self": 11825.80669318459 }, "steps_from_proto": { "total": 2546.2106976075374, "count": 2990826, "is_parallel": true, "self": 483.6643695834355, "children": { "_process_rank_one_or_two_observation": { "total": 2062.546328024102, "count": 11963304, "is_parallel": true, "self": 2062.546328024102 } } } } } } } } } } }, "trainer_advance": { "total": 43334.531104301845, "count": 1495413, "self": 265.390376212883, "children": { "process_trajectory": { "total": 7878.7989241888135, "count": 1495413, "self": 7873.1031263888435, "children": { "RLTrainer._checkpoint": { "total": 5.695797799970023, "count": 43, "self": 5.695797799970023 } } }, "_update_policy": { "total": 35190.34180390015, "count": 1043, "self": 3889.4235505988836, "children": { "TorchPOCAOptimizer.update": { "total": 31300.918253301264, "count": 31290, "self": 31300.918253301264 } } } } } } }, "trainer_threads": { "total": 1.1999945854768157e-06, "count": 1, "self": 1.1999945854768157e-06 }, "TrainerController._save_models": { "total": 0.13403679999464657, "count": 1, "self": 0.006410799993318506, "children": { "RLTrainer._checkpoint": { "total": 0.12762600000132807, "count": 1, "self": 0.12762600000132807 } } } } } } }