{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2354965209960938, "min": 3.1631598472595215, "max": 3.259577512741089, "count": 23 }, "SoccerTwos.Policy.Entropy.sum": { "value": 639437.625, "min": 44121.640625, "max": 701867.1875, "count": 23 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 717.6428571428571, "min": 421.0, "max": 908.8727272727273, "count": 23 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 200940.0, "min": 1684.0, "max": 202392.0, "count": 23 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1181.6961458115854, "min": 1181.6961458115854, "max": 1219.3582489601895, "count": 23 }, "SoccerTwos.Self-play.ELO.sum": { "value": 80355.3379151878, "min": 2424.2452100794476, "max": 185386.0257235947, "count": 23 }, "SoccerTwos.Step.mean": { "value": 4199362.0, "min": 1999986.0, "max": 4199362.0, "count": 23 }, "SoccerTwos.Step.sum": { "value": 4199362.0, "min": 1999986.0, "max": 4199362.0, "count": 23 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0049182092770934105, "min": -0.01564687490463257, "max": -0.0003157034807372838, "count": 23 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.6836310625076294, "min": -3.035493850708008, "max": -0.0003157034807372838, "count": 23 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.005050490144640207, "min": -0.01595248095691204, "max": -0.0002864261041395366, "count": 23 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.702018141746521, "min": -3.0947813987731934, "max": -0.0002864261041395366, "count": 23 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 23 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 23 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.045313668189396104, "min": -0.29986804239835935, "max": 0.5776000022888184, "count": 23 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.298599878326058, "min": -58.174400225281715, "max": 8.977200078777969, "count": 23 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.045313668189396104, "min": -0.29986804239835935, "max": 0.5776000022888184, "count": 23 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.298599878326058, "min": -58.174400225281715, "max": 8.977200078777969, "count": 23 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01799167172323602, "min": 0.014861049636662453, "max": 0.019059941363326893, "count": 22 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.0899583586161801, "min": 0.05944419854664981, "max": 0.09529970681663447, "count": 22 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00334238250933898, "min": 0.001252377344788632, "max": 0.007985346787609161, "count": 22 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0167119125466949, "min": 0.005071734591911081, "max": 0.0349894485824431, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003345942200394347, "min": 0.0012518831045148697, "max": 0.00804345243765662, "count": 22 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.016729711001971737, "min": 0.0050709672330413015, "max": 0.03572000410252561, "count": 22 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00015858042870979598, "min": 0.00015858042870979598, "max": 0.0001794705552647275, "count": 22 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00079290214354898, "min": 0.00063811456094276, "max": 0.0008925871337064599, "count": 22 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 22 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 1.25, "min": 1.0, "max": 1.25, "count": 22 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0079310913796, "min": 0.0079310913796, "max": 0.008974553722750002, "count": 22 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.039655456898, "min": 0.031913818276000004, "max": 0.044634724646, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693584801", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Giuseppe\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "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": "1693593423" }, "total": 8621.9649719, "count": 1, "self": 10.005873700001757, "children": { "run_training.setup": { "total": 0.11277470000000012, "count": 1, "self": 0.11277470000000012 }, "TrainerController.start_learning": { "total": 8611.8463235, "count": 1, "self": 4.054394300050262, "children": { "TrainerController._reset_env": { "total": 4.490738000001004, "count": 12, "self": 4.490738000001004 }, "TrainerController.advance": { "total": 8603.138268599949, "count": 143699, "self": 4.002740100238952, "children": { "env_step": { "total": 3074.1176869998617, "count": 143699, "self": 2343.9551613998215, "children": { "SubprocessEnvManager._take_step": { "total": 727.6576526000512, "count": 143699, "self": 24.159395099741346, "children": { "TorchPolicy.evaluate": { "total": 703.4982575003098, "count": 284784, "self": 703.4982575003098 } } }, "workers": { "total": 2.50487299998907, "count": 143699, "self": 0.0, "children": { "worker_root": { "total": 8584.451487899967, "count": 143699, "is_parallel": true, "self": 6712.165517899893, "children": { "steps_from_proto": { "total": 0.020495700000081385, "count": 24, "is_parallel": true, "self": 0.004654200004564402, "children": { "_process_rank_one_or_two_observation": { "total": 0.015841499995516983, "count": 96, "is_parallel": true, "self": 0.015841499995516983 } } }, "UnityEnvironment.step": { "total": 1872.2654743000744, "count": 143699, "is_parallel": true, "self": 86.01950960009935, "children": { "UnityEnvironment._generate_step_input": { "total": 75.04946119987738, "count": 143699, "is_parallel": true, "self": 75.04946119987738 }, "communicator.exchange": { "total": 1430.6941451998937, "count": 143699, "is_parallel": true, "self": 1430.6941451998937 }, "steps_from_proto": { "total": 280.50235830020387, "count": 287398, "is_parallel": true, "self": 61.095178400057534, "children": { "_process_rank_one_or_two_observation": { "total": 219.40717990014633, "count": 1149592, "is_parallel": true, "self": 219.40717990014633 } } } } } } } } } } }, "trainer_advance": { "total": 5525.017841499848, "count": 143699, "self": 30.893151299924284, "children": { "process_trajectory": { "total": 1268.068786899925, "count": 143699, "self": 1267.6742600999253, "children": { "RLTrainer._checkpoint": { "total": 0.3945267999998574, "count": 2, "self": 0.3945267999998574 } } }, "_update_policy": { "total": 4226.055903299999, "count": 103, "self": 378.2624287999797, "children": { "TorchPOCAOptimizer.update": { "total": 3847.7934745000193, "count": 3075, "self": 3847.7934745000193 } } } } } } }, "trainer_threads": { "total": 1.3999997463542968e-06, "count": 1, "self": 1.3999997463542968e-06 }, "TrainerController._save_models": { "total": 0.1629212000007101, "count": 1, "self": 4.300000182411168e-05, "children": { "RLTrainer._checkpoint": { "total": 0.16287819999888598, "count": 1, "self": 0.16287819999888598 } } } } } } }