{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.0015617740573361516, "min": 1.3637643860420212e-05, "max": 2.6758596897125244, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30.83566665649414, "min": 0.24638813734054565, "max": 84687.5625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 525.75, "min": 226.7, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 16824.0, "min": 10516.0, "max": 29916.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1220.2830960745177, "min": 1189.9265538848585, "max": 1245.1405939031679, "count": 458 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9762.264768596142, "min": 2388.9951739802627, "max": 42983.86648679155, "count": 458 }, "SoccerTwos.Step.mean": { "value": 4999056.0, "min": 9222.0, "max": 4999056.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999056.0, "min": 9222.0, "max": 4999056.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.16009820997714996, "min": -0.5137097835540771, "max": 1.8758513927459717, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.7216696739196777, "min": -9.760485649108887, "max": 20.63436508178711, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.15092705190181732, "min": -0.5354630351066589, "max": 1.9410430192947388, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.5657598972320557, "min": -10.173797607421875, "max": 25.233558654785156, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.2149647123673383, "min": -0.75, "max": 0.566027278249914, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.654400110244751, "min": -12.801200032234192, "max": 12.452600121498108, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.2149647123673383, "min": -0.75, "max": 0.566027278249914, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.654400110244751, "min": -12.801200032234192, "max": 12.452600121498108, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014961976895574481, "min": 0.0107762958718619, "max": 0.7321513732274373, "count": 234 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014961976895574481, "min": 0.0107762958718619, "max": 0.7321513732274373, "count": 234 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.03861832534894347, "min": 0.0014399651437997818, "max": 487.54074553114674, "count": 234 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.03861832534894347, "min": 0.0014399651437997818, "max": 487.54074553114674, "count": 234 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.038687607382113735, "min": 0.0019415066305858394, "max": 364.98830707916056, "count": 234 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.038687607382113735, "min": 0.0019415066305858394, "max": 364.98830707916056, "count": 234 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 234 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 234 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 234 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 234 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 234 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 234 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723480453", "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\\manug\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1723519387" }, "total": 38934.21318189999, "count": 1, "self": 0.42039139999542385, "children": { "run_training.setup": { "total": 0.15282989999104757, "count": 1, "self": 0.15282989999104757 }, "TrainerController.start_learning": { "total": 38933.639960600005, "count": 1, "self": 12.051619594727526, "children": { "TrainerController._reset_env": { "total": 8.8446104000177, "count": 25, "self": 8.8446104000177 }, "TrainerController.advance": { "total": 38912.562272305266, "count": 325775, "self": 12.287575501439278, "children": { "env_step": { "total": 9267.96440680472, "count": 325775, "self": 6937.4649534083, "children": { "SubprocessEnvManager._take_step": { "total": 2322.3707096003345, "count": 325775, "self": 85.78470509513863, "children": { "TorchPolicy.evaluate": { "total": 2236.586004505196, "count": 645218, "self": 2236.586004505196 } } }, "workers": { "total": 8.128743796085473, "count": 325775, "self": 0.0, "children": { "worker_root": { "total": 38910.34598830041, "count": 325775, "is_parallel": true, "self": 33586.3562564015, "children": { "steps_from_proto": { "total": 0.06664319999981672, "count": 50, "is_parallel": true, "self": 0.013479599947459064, "children": { "_process_rank_one_or_two_observation": { "total": 0.05316360005235765, "count": 200, "is_parallel": true, "self": 0.05316360005235765 } } }, "UnityEnvironment.step": { "total": 5323.92308869891, "count": 325775, "is_parallel": true, "self": 316.11133589592646, "children": { "UnityEnvironment._generate_step_input": { "total": 306.3323294022557, "count": 325775, "is_parallel": true, "self": 306.3323294022557 }, "communicator.exchange": { "total": 3686.6345395023673, "count": 325775, "is_parallel": true, "self": 3686.6345395023673 }, "steps_from_proto": { "total": 1014.8448838983604, "count": 651550, "is_parallel": true, "self": 206.0261990936997, "children": { "_process_rank_one_or_two_observation": { "total": 808.8186848046607, "count": 2606200, "is_parallel": true, "self": 808.8186848046607 } } } } } } } } } } }, "trainer_advance": { "total": 29632.310289999106, "count": 325775, "self": 87.13016979953682, "children": { "process_trajectory": { "total": 3465.300203099483, "count": 325775, "self": 3463.6139226994856, "children": { "RLTrainer._checkpoint": { "total": 1.6862803999974858, "count": 10, "self": 1.6862803999974858 } } }, "_update_policy": { "total": 26079.879917100086, "count": 234, "self": 1153.5283960004745, "children": { "TorchPOCAOptimizer.update": { "total": 24926.351521099612, "count": 7032, "self": 24926.351521099612 } } } } } } }, "trainer_threads": { "total": 1.5999976312741637e-06, "count": 1, "self": 1.5999976312741637e-06 }, "TrainerController._save_models": { "total": 0.18145669999648817, "count": 1, "self": 0.01026149999233894, "children": { "RLTrainer._checkpoint": { "total": 0.17119520000414923, "count": 1, "self": 0.17119520000414923 } } } } } } }