{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2103099822998047, "min": 2.201249837875366, "max": 3.2957518100738525, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44064.73828125, "min": 9530.1552734375, "max": 138095.359375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.58163265306123, "min": 40.56666666666667, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19436.0, "min": 6824.0, "max": 27180.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1462.9620152467444, "min": 1192.1950482485472, "max": 1467.2865805169836, "count": 415 }, "SoccerTwos.Self-play.ELO.sum": { "value": 286740.5549883619, "min": 2384.3900964970944, "max": 343788.7090882063, "count": 415 }, "SoccerTwos.Step.mean": { "value": 4999950.0, "min": 9128.0, "max": 4999950.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999950.0, "min": 9128.0, "max": 4999950.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007671913132071495, "min": -0.10139797627925873, "max": 0.18653760850429535, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.511366844177246, "min": -21.394973754882812, "max": 24.597007751464844, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.005279144272208214, "min": -0.10384976118803024, "max": 0.18847353756427765, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.0399913787841797, "min": -21.91230010986328, "max": 24.49136734008789, "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": -0.09802131937239981, "min": -0.6153846153846154, "max": 0.5238666711030183, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.310199916362762, "min": -46.71560001373291, "max": 51.93000000715256, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09802131937239981, "min": -0.6153846153846154, "max": 0.5238666711030183, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.310199916362762, "min": -46.71560001373291, "max": 51.93000000715256, "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": 0.018605794738202047, "min": 0.010871664331837868, "max": 0.022853191460793218, "count": 236 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018605794738202047, "min": 0.010871664331837868, "max": 0.022853191460793218, "count": 236 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10037734309832255, "min": 3.683921837212741e-07, "max": 0.10723397011558215, "count": 236 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10037734309832255, "min": 3.683921837212741e-07, "max": 0.10723397011558215, "count": 236 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10276271899541219, "min": 4.6114709941017886e-07, "max": 0.10958955039580663, "count": 236 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10276271899541219, "min": 4.6114709941017886e-07, "max": 0.10958955039580663, "count": 236 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 236 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 236 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 236 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 236 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 236 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 236 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733624626", "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": "\\\\?\\E:\\Anaconda\\envs\\drl7\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1733689629" }, "total": 65002.862883300055, "count": 1, "self": 0.4076301003806293, "children": { "run_training.setup": { "total": 0.11048809997737408, "count": 1, "self": 0.11048809997737408 }, "TrainerController.start_learning": { "total": 65002.3447650997, "count": 1, "self": 9.664195775054395, "children": { "TrainerController._reset_env": { "total": 6.51482770126313, "count": 25, "self": 6.51482770126313 }, "TrainerController.advance": { "total": 64986.00757572334, "count": 331947, "self": 9.779791821725667, "children": { "env_step": { "total": 7535.487085077912, "count": 331947, "self": 5999.420773681719, "children": { "SubprocessEnvManager._take_step": { "total": 1530.1518038650975, "count": 331947, "self": 53.8769374191761, "children": { "TorchPolicy.evaluate": { "total": 1476.2748664459214, "count": 638022, "self": 1476.2748664459214 } } }, "workers": { "total": 5.914507531095296, "count": 331947, "self": 0.0, "children": { "worker_root": { "total": 64985.299433196895, "count": 331947, "is_parallel": true, "self": 60197.410073976964, "children": { "steps_from_proto": { "total": 0.051801799796521664, "count": 50, "is_parallel": true, "self": 0.010555502958595753, "children": { "_process_rank_one_or_two_observation": { "total": 0.04124629683792591, "count": 200, "is_parallel": true, "self": 0.04124629683792591 } } }, "UnityEnvironment.step": { "total": 4787.8375574201345, "count": 331947, "is_parallel": true, "self": 229.60771071817726, "children": { "UnityEnvironment._generate_step_input": { "total": 208.17352842446417, "count": 331947, "is_parallel": true, "self": 208.17352842446417 }, "communicator.exchange": { "total": 3581.358097888995, "count": 331947, "is_parallel": true, "self": 3581.358097888995 }, "steps_from_proto": { "total": 768.6982203884982, "count": 663894, "is_parallel": true, "self": 152.91460758028552, "children": { "_process_rank_one_or_two_observation": { "total": 615.7836128082126, "count": 2655576, "is_parallel": true, "self": 615.7836128082126 } } } } } } } } } } }, "trainer_advance": { "total": 57440.740698823705, "count": 331947, "self": 59.941079049836844, "children": { "process_trajectory": { "total": 1198.5999041702598, "count": 331947, "self": 1196.859120070003, "children": { "RLTrainer._checkpoint": { "total": 1.7407841002568603, "count": 10, "self": 1.7407841002568603 } } }, "_update_policy": { "total": 56182.19971560361, "count": 236, "self": 801.2737847049721, "children": { "TorchPOCAOptimizer.update": { "total": 55380.92593089864, "count": 7092, "self": 55380.92593089864 } } } } } } }, "trainer_threads": { "total": 9.0012326836586e-07, "count": 1, "self": 9.0012326836586e-07 }, "TrainerController._save_models": { "total": 0.15816499991342425, "count": 1, "self": 0.004409899935126305, "children": { "RLTrainer._checkpoint": { "total": 0.15375509997829795, "count": 1, "self": 0.15375509997829795 } } } } } } }