{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.237565279006958, "min": 3.20178484916687, "max": 3.2957546710968018, "count": 40 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55530.71875, "min": 28502.75390625, "max": 115166.796875, "count": 40 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 514.2222222222222, "max": 999.0, "count": 40 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 11988.0, "max": 27704.0, "count": 40 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1196.1062358378217, "min": 1195.4793932780042, "max": 1200.987212560798, "count": 27 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4784.424943351287, "min": 2391.683368924628, "max": 12005.430052443306, "count": 27 }, "SoccerTwos.Step.mean": { "value": 399178.0, "min": 9622.0, "max": 399178.0, "count": 40 }, "SoccerTwos.Step.sum": { "value": 399178.0, "min": 9622.0, "max": 399178.0, "count": 40 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0014672715915367007, "min": -0.0570068359375, "max": 0.0038764458149671555, "count": 40 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.014672716148197651, "min": -0.9120469093322754, "max": 0.038764458149671555, "count": 40 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0008330975542776287, "min": -0.05705248937010765, "max": 0.0043180277571082115, "count": 40 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.008330975659191608, "min": -0.9127935767173767, "max": 0.043180279433727264, "count": 40 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 40 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 40 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.5714285714285714, "max": 0.20032499730587006, "count": 40 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -8.0, "max": 3.205199956893921, "count": 40 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5714285714285714, "max": 0.20032499730587006, "count": 40 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -8.0, "max": 3.205199956893921, "count": 40 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019485128942566612, "min": 0.012845803144106565, "max": 0.019524715081691586, "count": 18 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019485128942566612, "min": 0.012845803144106565, "max": 0.019524715081691586, "count": 18 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.001545818014225612, "min": 3.117751069415438e-05, "max": 0.0036863998975604773, "count": 18 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.001545818014225612, "min": 3.117751069415438e-05, "max": 0.0036863998975604773, "count": 18 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0015514041083709647, "min": 3.020791276261055e-05, "max": 0.003695178482060631, "count": 18 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0015514041083709647, "min": 3.020791276261055e-05, "max": 0.003695178482060631, "count": 18 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 18 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 18 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 18 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 18 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 18 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 18 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1743685776", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/Users/xh0543/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/mac/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": "2.6.0", "numpy_version": "1.23.5", "end_time_seconds": "1743687266" }, "total": 1489.865813124925, "count": 1, "self": 0.23239341587759554, "children": { "run_training.setup": { "total": 0.02430645888671279, "count": 1, "self": 0.02430645888671279 }, "TrainerController.start_learning": { "total": 1489.6091132501606, "count": 1, "self": 0.30734025756828487, "children": { "TrainerController._reset_env": { "total": 2.9361748329829425, "count": 2, "self": 2.9361748329829425 }, "TrainerController.advance": { "total": 1486.0469901596662, "count": 25915, "self": 0.28386256704106927, "children": { "env_step": { "total": 1185.7854265163187, "count": 25915, "self": 1126.2829711791128, "children": { "SubprocessEnvManager._take_step": { "total": 59.29873785516247, "count": 25915, "self": 1.4247417531441897, "children": { "TorchPolicy.evaluate": { "total": 57.87399610201828, "count": 51504, "self": 57.87399610201828 } } }, "workers": { "total": 0.2037174820434302, "count": 25915, "self": 0.0, "children": { "worker_root": { "total": 1486.4332666655537, "count": 25915, "is_parallel": true, "self": 406.8210734075401, "children": { "steps_from_proto": { "total": 0.0029479179065674543, "count": 4, "is_parallel": true, "self": 0.0003624584060162306, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025854595005512238, "count": 16, "is_parallel": true, "self": 0.0025854595005512238 } } }, "UnityEnvironment.step": { "total": 1079.609245340107, "count": 25915, "is_parallel": true, "self": 3.344203945249319, "children": { "UnityEnvironment._generate_step_input": { "total": 19.141762213082984, "count": 25915, "is_parallel": true, "self": 19.141762213082984 }, "communicator.exchange": { "total": 1017.5508399074897, "count": 25915, "is_parallel": true, "self": 1017.5508399074897 }, "steps_from_proto": { "total": 39.57243927428499, "count": 51830, "is_parallel": true, "self": 4.565850911894813, "children": { "_process_rank_one_or_two_observation": { "total": 35.006588362390175, "count": 207320, "is_parallel": true, "self": 35.006588362390175 } } } } } } } } } } }, "trainer_advance": { "total": 299.9777010763064, "count": 25915, "self": 2.482819141354412, "children": { "process_trajectory": { "total": 44.548288392368704, "count": 25915, "self": 44.548288392368704 }, "_update_policy": { "total": 252.9465935425833, "count": 18, "self": 24.602285619359463, "children": { "TorchPOCAOptimizer.update": { "total": 228.34430792322382, "count": 546, "self": 228.34430792322382 } } } } } } }, "trainer_threads": { "total": 5.83939254283905e-07, "count": 1, "self": 5.83939254283905e-07 }, "TrainerController._save_models": { "total": 0.3186074160039425, "count": 1, "self": 0.00224791606888175, "children": { "RLTrainer._checkpoint": { "total": 0.31635949993506074, "count": 1, "self": 0.31635949993506074 } } } } } } }