{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.273096799850464, "min": 3.2668933868408203, "max": 3.295724868774414, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37077.640625, "min": 37077.640625, "max": 107257.7421875, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 772.8333333333334, "min": 409.1666666666667, "max": 999.0, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18548.0, "min": 15132.0, "max": 27536.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.1048419078513, "min": 1197.3351400713882, "max": 1202.1048419078513, "count": 9 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7212.629051447108, "min": 2394.6702801427764, "max": 16781.732370544243, "count": 9 }, "SoccerTwos.Step.mean": { "value": 99835.0, "min": 9788.0, "max": 99835.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 99835.0, "min": 9788.0, "max": 99835.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0485982783138752, "min": -0.0969996526837349, "max": -0.0485982783138752, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5831793546676636, "min": -1.7221587896347046, "max": -0.5617256164550781, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04743114486336708, "min": -0.09698408842086792, "max": -0.04743114486336708, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.5691737532615662, "min": -1.7347235679626465, "max": -0.5584996342658997, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.22946666677792868, "min": -0.4254250004887581, "max": 0.20239999890327454, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.753600001335144, "min": -6.806800007820129, "max": 3.7979999780654907, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.22946666677792868, "min": -0.4254250004887581, "max": 0.20239999890327454, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.753600001335144, "min": -6.806800007820129, "max": 3.7979999780654907, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018837112501690473, "min": 0.011768401923472994, "max": 0.018837112501690473, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018837112501690473, "min": 0.011768401923472994, "max": 0.018837112501690473, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.001745747074407215, "min": 0.0013953256459596256, "max": 0.007921716229369243, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.001745747074407215, "min": 0.0013953256459596256, "max": 0.007921716229369243, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0017536110477522015, "min": 0.0013969194435048849, "max": 0.007526869854579369, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0017536110477522015, "min": 0.0013969194435048849, "max": 0.007526869854579369, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686402403", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./SoccerTwos.yaml --env ./ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id SoccerTwo --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686402973" }, "total": 570.6112363320001, "count": 1, "self": 0.5389801770002123, "children": { "run_training.setup": { "total": 0.06431903599991529, "count": 1, "self": 0.06431903599991529 }, "TrainerController.start_learning": { "total": 570.007937119, "count": 1, "self": 0.28256211299753886, "children": { "TrainerController._reset_env": { "total": 1.8835971869996229, "count": 2, "self": 1.8835971869996229 }, "TrainerController.advance": { "total": 567.4930995030027, "count": 7225, "self": 0.2787904750009602, "children": { "env_step": { "total": 258.1835296370007, "count": 7225, "self": 212.23751650999384, "children": { "SubprocessEnvManager._take_step": { "total": 45.76937661199872, "count": 7225, "self": 1.6032072839859666, "children": { "TorchPolicy.evaluate": { "total": 44.16616932801276, "count": 14350, "self": 44.16616932801276 } } }, "workers": { "total": 0.17663651500811284, "count": 7225, "self": 0.0, "children": { "worker_root": { "total": 567.7389741700101, "count": 7225, "is_parallel": true, "self": 392.33588427904556, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0084156069999608, "count": 2, "is_parallel": true, "self": 0.005412873999603107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030027330003576935, "count": 8, "is_parallel": true, "self": 0.0030027330003576935 } } }, "UnityEnvironment.step": { "total": 0.07044513400001051, "count": 1, "is_parallel": true, "self": 0.0013436229999115312, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0014680570000109583, "count": 1, "is_parallel": true, "self": 0.0014680570000109583 }, "communicator.exchange": { "total": 0.06282397099994341, "count": 1, "is_parallel": true, "self": 0.06282397099994341 }, "steps_from_proto": { "total": 0.00480948300014461, "count": 2, "is_parallel": true, "self": 0.0009365330001855909, "children": { "_process_rank_one_or_two_observation": { "total": 0.003872949999959019, "count": 8, "is_parallel": true, "self": 0.003872949999959019 } } } } } } }, "UnityEnvironment.step": { "total": 175.40078959896482, "count": 7224, "is_parallel": true, "self": 9.913494993955737, "children": { "UnityEnvironment._generate_step_input": { "total": 6.261065245018699, "count": 7224, "is_parallel": true, "self": 6.261065245018699 }, "communicator.exchange": { "total": 124.5604742050109, "count": 7224, "is_parallel": true, "self": 124.5604742050109 }, "steps_from_proto": { "total": 34.66575515497948, "count": 14448, "is_parallel": true, "self": 6.376640015944076, "children": { "_process_rank_one_or_two_observation": { "total": 28.289115139035403, "count": 57792, "is_parallel": true, "self": 28.289115139035403 } } } } }, "steps_from_proto": { "total": 0.002300291999745241, "count": 2, "is_parallel": true, "self": 0.0004718130007859145, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018284789989593264, "count": 8, "is_parallel": true, "self": 0.0018284789989593264 } } } } } } } } }, "trainer_advance": { "total": 309.03077939100103, "count": 7225, "self": 1.7174269240124431, "children": { "process_trajectory": { "total": 40.6562813089879, "count": 7225, "self": 40.6562813089879 }, "_update_policy": { "total": 266.6570711580007, "count": 4, "self": 23.40013348399816, "children": { "TorchPOCAOptimizer.update": { "total": 243.25693767400253, "count": 120, "self": 243.25693767400253 } } } } } } }, "trainer_threads": { "total": 1.3059998309472576e-06, "count": 1, "self": 1.3059998309472576e-06 }, "TrainerController._save_models": { "total": 0.3486770100003014, "count": 1, "self": 0.0019965860005868308, "children": { "RLTrainer._checkpoint": { "total": 0.34668042399971455, "count": 1, "self": 0.34668042399971455 } } } } } } }