{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.240445375442505, "min": 3.2071869373321533, "max": 3.2956974506378174, "count": 27 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45003.3046875, "min": 22694.2578125, "max": 105462.3125, "count": 27 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 726.5, "min": 525.875, "max": 999.0, "count": 27 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17436.0, "min": 16828.0, "max": 24800.0, "count": 27 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1193.7578446427165, "min": 1191.414963979109, "max": 1197.5518243297993, "count": 26 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4775.031378570866, "min": 2384.2387313629906, "max": 19143.40770044412, "count": 26 }, "SoccerTwos.Step.mean": { "value": 269976.0, "min": 9420.0, "max": 269976.0, "count": 27 }, "SoccerTwos.Step.sum": { "value": 269976.0, "min": 9420.0, "max": 269976.0, "count": 27 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014902826398611069, "min": -0.02239292860031128, "max": 0.0017403720412403345, "count": 27 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.1937367469072342, "min": -0.35947346687316895, "max": 0.029586324468255043, "count": 27 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.011990911327302456, "min": -0.014891309663653374, "max": -0.002565356669947505, "count": 27 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.1558818519115448, "min": -0.23826095461845398, "max": -0.0343497060239315, "count": 27 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 27 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 27 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.042861534998967096, "min": -0.6866823504952824, "max": 0.08849411852219526, "count": 27 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.5571999549865723, "min": -11.6735999584198, "max": 1.5044000148773193, "count": 27 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.042861534998967096, "min": -0.6866823504952824, "max": 0.08849411852219526, "count": 27 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.5571999549865723, "min": -11.6735999584198, "max": 1.5044000148773193, "count": 27 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 27 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 27 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.010117768005390342, "min": 0.010117768005390342, "max": 0.01865373881882988, "count": 12 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.010117768005390342, "min": 0.010117768005390342, "max": 0.01865373881882988, "count": 12 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003935955084549884, "min": 0.001508021573924149, "max": 0.007247587277864416, "count": 12 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003935955084549884, "min": 0.001508021573924149, "max": 0.007247587277864416, "count": 12 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003937759677258631, "min": 0.0015174899871150652, "max": 0.007255641728018721, "count": 12 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003937759677258631, "min": 0.0015174899871150652, "max": 0.007255641728018721, "count": 12 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 12 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 12 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 12 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 12 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 12 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 12 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731312250", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1", "numpy_version": "1.23.5", "end_time_seconds": "1731313487" }, "total": 1236.545987957972, "count": 1, "self": 0.004797665984369814, "children": { "run_training.setup": { "total": 0.01639762509148568, "count": 1, "self": 0.01639762509148568 }, "TrainerController.start_learning": { "total": 1236.5247926668962, "count": 1, "self": 0.22838388779200613, "children": { "TrainerController._reset_env": { "total": 4.5475917919538915, "count": 2, "self": 4.5475917919538915 }, "TrainerController.advance": { "total": 1231.0880667380989, "count": 17821, "self": 0.21842296177055687, "children": { "env_step": { "total": 992.9914524647174, "count": 17821, "self": 954.8745469633723, "children": { "SubprocessEnvManager._take_step": { "total": 37.965532288653776, "count": 17821, "self": 1.1281631885794923, "children": { "TorchPolicy.evaluate": { "total": 36.837369100074284, "count": 35360, "self": 36.837369100074284 } } }, "workers": { "total": 0.15137321269139647, "count": 17820, "self": 0.0, "children": { "worker_root": { "total": 1231.8887167989742, "count": 17820, "is_parallel": true, "self": 306.9543487156043, "children": { "steps_from_proto": { "total": 0.00428250094410032, "count": 4, "is_parallel": true, "self": 0.0006960829487070441, "children": { "_process_rank_one_or_two_observation": { "total": 0.003586417995393276, "count": 16, "is_parallel": true, "self": 0.003586417995393276 } } }, "UnityEnvironment.step": { "total": 924.9300855824258, "count": 17820, "is_parallel": true, "self": 2.6337445022072643, "children": { "UnityEnvironment._generate_step_input": { "total": 15.928510103025474, "count": 17820, "is_parallel": true, "self": 15.928510103025474 }, "communicator.exchange": { "total": 872.163203357486, "count": 17820, "is_parallel": true, "self": 872.163203357486 }, "steps_from_proto": { "total": 34.204627619707026, "count": 35640, "is_parallel": true, "self": 3.7891682606423274, "children": { "_process_rank_one_or_two_observation": { "total": 30.415459359064698, "count": 142560, "is_parallel": true, "self": 30.415459359064698 } } } } } } } } } } }, "trainer_advance": { "total": 237.87819131161086, "count": 17820, "self": 2.284961257711984, "children": { "process_trajectory": { "total": 34.421652843710035, "count": 17820, "self": 34.421652843710035 }, "_update_policy": { "total": 201.17157721018884, "count": 12, "self": 19.691816289327107, "children": { "TorchPOCAOptimizer.update": { "total": 181.47976092086174, "count": 360, "self": 181.47976092086174 } } } } } } }, "trainer_threads": { "total": 9.579816833138466e-07, "count": 1, "self": 9.579816833138466e-07 }, "TrainerController._save_models": { "total": 0.6607492910698056, "count": 1, "self": 0.0020934580825269222, "children": { "RLTrainer._checkpoint": { "total": 0.6586558329872787, "count": 1, "self": 0.6586558329872787 } } } } } } }