{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.280280113220215, "min": 3.2783467769622803, "max": 3.2957565784454346, "count": 6 }, "SoccerTwos.Policy.Entropy.sum": { "value": 84185.109375, "min": 48556.515625, "max": 105464.2109375, "count": 6 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 863.6666666666666, "min": 628.0, "max": 999.0, "count": 6 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20728.0, "min": 19100.0, "max": 20796.0, "count": 6 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.2824431324761, "min": 1198.03718369126, "max": 1202.2824431324761, "count": 5 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7213.694658794857, "min": 4792.14873476504, "max": 9607.354611621628, "count": 5 }, "SoccerTwos.Step.mean": { "value": 59472.0, "min": 9064.0, "max": 59472.0, "count": 6 }, "SoccerTwos.Step.sum": { "value": 59472.0, "min": 9064.0, "max": 59472.0, "count": 6 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.04934411123394966, "min": -0.07580116391181946, "max": -0.04934411123394966, "count": 6 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5921293497085571, "min": -1.1370174884796143, "max": -0.5921293497085571, "count": 6 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04930315539240837, "min": -0.07575174421072006, "max": -0.04930315539240837, "count": 6 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.5916378498077393, "min": -1.1362628936767578, "max": -0.5916378498077393, "count": 6 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 6 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.31566666687528294, "min": -0.31618666648864746, "max": 0.07618571392127446, "count": 6 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.788000002503395, "min": -4.742799997329712, "max": 1.0665999948978424, "count": 6 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.31566666687528294, "min": -0.31618666648864746, "max": 0.07618571392127446, "count": 6 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.788000002503395, "min": -4.742799997329712, "max": 1.0665999948978424, "count": 6 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012926523063045654, "min": 0.012926523063045654, "max": 0.020022281814211357, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012926523063045654, "min": 0.012926523063045654, "max": 0.020022281814211357, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.002601245115511119, "min": 0.002601245115511119, "max": 0.003279344812552962, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.002601245115511119, "min": 0.002601245115511119, "max": 0.003279344812552962, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0026231462019495667, "min": 0.0026231462019495667, "max": 0.002986939672458296, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0026231462019495667, "min": 0.0026231462019495667, "max": 0.002986939672458296, "count": 2 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724519447", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/opt/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1724520140" }, "total": 693.4518482399999, "count": 1, "self": 0.05742895299954398, "children": { "run_training.setup": { "total": 0.40264591000004657, "count": 1, "self": 0.40264591000004657 }, "TrainerController.start_learning": { "total": 692.9917733770003, "count": 1, "self": 0.12369536600908759, "children": { "TrainerController._reset_env": { "total": 7.406253436000043, "count": 1, "self": 7.406253436000043 }, "TrainerController.advance": { "total": 685.071366134991, "count": 4785, "self": 0.12215116300012596, "children": { "env_step": { "total": 592.8307875299761, "count": 4785, "self": 573.5621467529818, "children": { "SubprocessEnvManager._take_step": { "total": 19.187191830997108, "count": 4785, "self": 0.7303791650201674, "children": { "TorchPolicy.evaluate": { "total": 18.45681266597694, "count": 9508, "self": 18.45681266597694 } } }, "workers": { "total": 0.081448945997181, "count": 4784, "self": 0.0, "children": { "worker_root": { "total": 686.8875139429874, "count": 4784, "is_parallel": true, "self": 128.84188381700505, "children": { "steps_from_proto": { "total": 0.0035839239999404526, "count": 2, "is_parallel": true, "self": 0.0006243819998417166, "children": { "_process_rank_one_or_two_observation": { "total": 0.002959542000098736, "count": 8, "is_parallel": true, "self": 0.002959542000098736 } } }, "UnityEnvironment.step": { "total": 558.0420462019824, "count": 4784, "is_parallel": true, "self": 1.7412149479487198, "children": { "UnityEnvironment._generate_step_input": { "total": 10.846042801002113, "count": 4784, "is_parallel": true, "self": 10.846042801002113 }, "communicator.exchange": { "total": 525.9501560759873, "count": 4784, "is_parallel": true, "self": 525.9501560759873 }, "steps_from_proto": { "total": 19.504632377044345, "count": 9568, "is_parallel": true, "self": 2.6491153230367672, "children": { "_process_rank_one_or_two_observation": { "total": 16.855517054007578, "count": 38272, "is_parallel": true, "self": 16.855517054007578 } } } } } } } } } } }, "trainer_advance": { "total": 92.11842744201476, "count": 4784, "self": 0.7905554330382074, "children": { "process_trajectory": { "total": 12.927446241976668, "count": 4784, "self": 12.927446241976668 }, "_update_policy": { "total": 78.40042576699989, "count": 2, "self": 7.863874345997829, "children": { "TorchPOCAOptimizer.update": { "total": 70.53655142100206, "count": 66, "self": 70.53655142100206 } } } } } } }, "trainer_threads": { "total": 1.9780000002356246e-06, "count": 1, "self": 1.9780000002356246e-06 }, "TrainerController._save_models": { "total": 0.390456462000202, "count": 1, "self": 0.013004382999952213, "children": { "RLTrainer._checkpoint": { "total": 0.3774520790002498, "count": 1, "self": 0.3774520790002498 } } } } } } }