{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.147101402282715, "min": 3.1347227096557617, "max": 3.295729875564575, "count": 102 }, "SoccerTwos.Policy.Entropy.sum": { "value": 77947.40625, "min": 16356.080078125, "max": 114345.3828125, "count": 102 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 770.5714285714286, "min": 400.4166666666667, "max": 999.0, "count": 102 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21576.0, "min": 15984.0, "max": 26476.0, "count": 102 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.313516757205, "min": 1193.8793208087604, "max": 1206.2091219196768, "count": 80 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4809.25406702882, "min": 2387.758641617521, "max": 16882.68316522321, "count": 80 }, "SoccerTwos.Step.mean": { "value": 1019978.0, "min": 9258.0, "max": 1019978.0, "count": 102 }, "SoccerTwos.Step.sum": { "value": 1019978.0, "min": 9258.0, "max": 1019978.0, "count": 102 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006806105375289917, "min": -0.02353421039879322, "max": 0.05611564964056015, "count": 102 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.09528547525405884, "min": -0.35667768120765686, "max": 0.8646183609962463, "count": 102 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.007018849719315767, "min": -0.023532651364803314, "max": 0.05485215410590172, "count": 102 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.09826389700174332, "min": -0.38856056332588196, "max": 0.8649909496307373, "count": 102 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 102 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 102 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.043971427849360874, "min": -0.5625, "max": 0.421424999833107, "count": 102 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.6155999898910522, "min": -9.0, "max": 6.742799997329712, "count": 102 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.043971427849360874, "min": -0.5625, "max": 0.421424999833107, "count": 102 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.6155999898910522, "min": -9.0, "max": 6.742799997329712, "count": 102 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 102 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 102 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.026190954120465904, "min": 0.017752926692588114, "max": 0.029721519795324034, "count": 47 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.026190954120465904, "min": 0.017752926692588114, "max": 0.029721519795324034, "count": 47 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0024965836385187385, "min": 1.735671965376703e-05, "max": 0.004415038612205535, "count": 47 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0024965836385187385, "min": 1.735671965376703e-05, "max": 0.004415038612205535, "count": 47 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002494325729397436, "min": 1.8433181081953022e-05, "max": 0.004428144593839533, "count": 47 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002494325729397436, "min": 1.8433181081953022e-05, "max": 0.004428144593839533, "count": 47 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003000000000000001, "min": 0.0003000000000000001, "max": 0.0003000000000000002, "count": 47 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003000000000000001, "min": 0.0003000000000000001, "max": 0.0003000000000000002, "count": 47 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.19999999999999993, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 47 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.19999999999999993, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 47 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 47 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 47 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744731466", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/uccacbo/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-v0 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744733695" }, "total": 2300.4130689190006, "count": 1, "self": 0.08447929999965709, "children": { "run_training.setup": { "total": 0.0216489399999773, "count": 1, "self": 0.0216489399999773 }, "TrainerController.start_learning": { "total": 2300.306940679001, "count": 1, "self": 1.4889187380467774, "children": { "TrainerController._reset_env": { "total": 2.787369712002146, "count": 6, "self": 2.787369712002146 }, "TrainerController.advance": { "total": 2295.7306413619517, "count": 67389, "self": 1.7760885351908655, "children": { "env_step": { "total": 1906.0590865838867, "count": 67389, "self": 1235.865202776975, "children": { "SubprocessEnvManager._take_step": { "total": 669.1899649339093, "count": 67389, "self": 10.862101765071202, "children": { "TorchPolicy.evaluate": { "total": 658.3278631688381, "count": 133806, "self": 658.3278631688381 } } }, "workers": { "total": 1.0039188730024762, "count": 67388, "self": 0.0, "children": { "worker_root": { "total": 2297.0736649838, "count": 67388, "is_parallel": true, "self": 1239.32249726183, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026662180007406278, "count": 2, "is_parallel": true, "self": 0.0008137830000123358, "children": { "_process_rank_one_or_two_observation": { "total": 0.001852435000728292, "count": 8, "is_parallel": true, "self": 0.001852435000728292 } } }, "UnityEnvironment.step": { "total": 0.030667754000205605, "count": 1, "is_parallel": true, "self": 0.0005541290001929156, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004965200005244697, "count": 1, "is_parallel": true, "self": 0.0004965200005244697 }, "communicator.exchange": { "total": 0.028032208999320574, "count": 1, "is_parallel": true, "self": 0.028032208999320574 }, "steps_from_proto": { "total": 0.001584896000167646, "count": 2, "is_parallel": true, "self": 0.0003713910000442411, "children": { "_process_rank_one_or_two_observation": { "total": 0.001213505000123405, "count": 8, "is_parallel": true, "self": 0.001213505000123405 } } } } } } }, "UnityEnvironment.step": { "total": 1057.7424493939707, "count": 67387, "is_parallel": true, "self": 32.51656335466214, "children": { "UnityEnvironment._generate_step_input": { "total": 19.8924221168636, "count": 67387, "is_parallel": true, "self": 19.8924221168636 }, "communicator.exchange": { "total": 907.758916745006, "count": 67387, "is_parallel": true, "self": 907.758916745006 }, "steps_from_proto": { "total": 97.57454717743894, "count": 134774, "is_parallel": true, "self": 20.51235802046631, "children": { "_process_rank_one_or_two_observation": { "total": 77.06218915697264, "count": 539096, "is_parallel": true, "self": 77.06218915697264 } } } } }, "steps_from_proto": { "total": 0.008718327999304165, "count": 10, "is_parallel": true, "self": 0.0018642610002643778, "children": { "_process_rank_one_or_two_observation": { "total": 0.006854066999039787, "count": 40, "is_parallel": true, "self": 0.006854066999039787 } } } } } } } } }, "trainer_advance": { "total": 387.89546624287414, "count": 67388, "self": 11.408661232801023, "children": { "process_trajectory": { "total": 130.86192820807537, "count": 67388, "self": 130.12915453507594, "children": { "RLTrainer._checkpoint": { "total": 0.7327736729994285, "count": 2, "self": 0.7327736729994285 } } }, "_update_policy": { "total": 245.62487680199774, "count": 47, "self": 100.96191203600938, "children": { "TorchPOCAOptimizer.update": { "total": 144.66296476598836, "count": 2901, "self": 144.66296476598836 } } } } } } }, "trainer_threads": { "total": 9.409995982423425e-07, "count": 1, "self": 9.409995982423425e-07 }, "TrainerController._save_models": { "total": 0.30000992600071186, "count": 1, "self": 0.003420989001824637, "children": { "RLTrainer._checkpoint": { "total": 0.2965889369988872, "count": 1, "self": 0.2965889369988872 } } } } } } }