{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8695679903030396, "min": 1.8561608791351318, "max": 3.2957324981689453, "count": 741 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37511.01171875, "min": 14374.3935546875, "max": 131923.46875, "count": 741 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 74.15384615384616, "min": 41.36974789915966, "max": 999.0, "count": 741 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19280.0, "min": 14028.0, "max": 27756.0, "count": 741 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1601.087643019408, "min": 1197.055581097732, "max": 1619.8735147975078, "count": 709 }, "SoccerTwos.Self-play.ELO.sum": { "value": 208141.39359252303, "min": 2396.657233428197, "max": 377081.69390390615, "count": 709 }, "SoccerTwos.Step.mean": { "value": 7409936.0, "min": 9894.0, "max": 7409936.0, "count": 741 }, "SoccerTwos.Step.sum": { "value": 7409936.0, "min": 9894.0, "max": 7409936.0, "count": 741 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014496799558401108, "min": -0.1171058714389801, "max": 0.20744945108890533, "count": 741 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.899080753326416, "min": -19.87245750427246, "max": 27.615901947021484, "count": 741 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.010194798931479454, "min": -0.12086234986782074, "max": 0.20504526793956757, "count": 741 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.335518717765808, "min": -20.733966827392578, "max": 26.297012329101562, "count": 741 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 741 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 741 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04834198314724988, "min": -0.6237600008646648, "max": 0.48357390903908276, "count": 741 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.332799792289734, "min": -54.086000204086304, "max": 61.03159999847412, "count": 741 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04834198314724988, "min": -0.6237600008646648, "max": 0.48357390903908276, "count": 741 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.332799792289734, "min": -54.086000204086304, "max": 61.03159999847412, "count": 741 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 741 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 741 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016808574992076806, "min": 0.009887452382827178, "max": 0.023939259319255748, "count": 355 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016808574992076806, "min": 0.009887452382827178, "max": 0.023939259319255748, "count": 355 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10378332709272703, "min": 5.960457716961779e-06, "max": 0.1252267780403296, "count": 355 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10378332709272703, "min": 5.960457716961779e-06, "max": 0.1252267780403296, "count": 355 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10573393156131108, "min": 6.812734454797464e-06, "max": 0.1279440276324749, "count": 355 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10573393156131108, "min": 6.812734454797464e-06, "max": 0.1279440276324749, "count": 355 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 355 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 355 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 355 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 355 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 355 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 355 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718897448", "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\POCs\\RAG\\deep-rl\\ml-agents\\venv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1718948482" }, "total": 51033.824782700016, "count": 1, "self": 0.03263080000760965, "children": { "run_training.setup": { "total": 1.4725668000173755, "count": 1, "self": 1.4725668000173755 }, "TrainerController.start_learning": { "total": 51032.31958509999, "count": 1, "self": 25.484635114320554, "children": { "TrainerController._reset_env": { "total": 51.38374520002981, "count": 38, "self": 51.38374520002981 }, "TrainerController.advance": { "total": 50954.992948485655, "count": 502179, "self": 26.751977856765734, "children": { "env_step": { "total": 22406.75197801474, "count": 502179, "self": 16473.023351420707, "children": { "SubprocessEnvManager._take_step": { "total": 5918.248750693747, "count": 502179, "self": 169.12540848905337, "children": { "TorchPolicy.evaluate": { "total": 5749.1233422046935, "count": 938788, "self": 5749.1233422046935 } } }, "workers": { "total": 15.47987590028788, "count": 502179, "self": 0.0, "children": { "worker_root": { "total": 50943.18143299091, "count": 502179, "is_parallel": true, "self": 37682.81295509299, "children": { "steps_from_proto": { "total": 0.19373509986326098, "count": 76, "is_parallel": true, "self": 0.033987099886871874, "children": { "_process_rank_one_or_two_observation": { "total": 0.1597479999763891, "count": 304, "is_parallel": true, "self": 0.1597479999763891 } } }, "UnityEnvironment.step": { "total": 13260.174742798059, "count": 502179, "is_parallel": true, "self": 764.8212337167934, "children": { "UnityEnvironment._generate_step_input": { "total": 608.9368677975144, "count": 502179, "is_parallel": true, "self": 608.9368677975144 }, "communicator.exchange": { "total": 9446.068704087433, "count": 502179, "is_parallel": true, "self": 9446.068704087433 }, "steps_from_proto": { "total": 2440.3479371963185, "count": 1004358, "is_parallel": true, "self": 433.59629521882744, "children": { "_process_rank_one_or_two_observation": { "total": 2006.751641977491, "count": 4017432, "is_parallel": true, "self": 2006.751641977491 } } } } } } } } } } }, "trainer_advance": { "total": 28521.488992614148, "count": 502179, "self": 172.43458791816374, "children": { "process_trajectory": { "total": 5132.9358505963755, "count": 502179, "self": 5127.567651396355, "children": { "RLTrainer._checkpoint": { "total": 5.368199200020172, "count": 14, "self": 5.368199200020172 } } }, "_update_policy": { "total": 23216.11855409961, "count": 356, "self": 2201.4250492994033, "children": { "TorchPOCAOptimizer.update": { "total": 21014.693504800205, "count": 10660, "self": 21014.693504800205 } } } } } } }, "trainer_threads": { "total": 2.6999914553016424e-06, "count": 1, "self": 2.6999914553016424e-06 }, "TrainerController._save_models": { "total": 0.4582535999943502, "count": 1, "self": 0.021307299990439788, "children": { "RLTrainer._checkpoint": { "total": 0.43694630000391044, "count": 1, "self": 0.43694630000391044 } } } } } } }