{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.13089656829834, "min": 3.13089656829834, "max": 3.151585340499878, "count": 5 }, "SoccerTwos.Policy.Entropy.sum": { "value": 75141.515625, "min": 27924.60546875, "max": 100850.734375, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 662.375, "min": 426.625, "max": 924.2, "count": 5 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21196.0, "min": 13652.0, "max": 24844.0, "count": 5 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1196.334176818747, "min": 1196.2992538829644, "max": 1197.4207923472334, "count": 5 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9570.673414549976, "min": 4786.589945410005, "max": 14369.0495081668, "count": 5 }, "SoccerTwos.Step.mean": { "value": 599676.0, "min": 559051.0, "max": 599676.0, "count": 5 }, "SoccerTwos.Step.sum": { "value": 599676.0, "min": 559051.0, "max": 599676.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.018645934760570526, "min": -0.020072979852557182, "max": -0.010313838720321655, "count": 5 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.2983349561691284, "min": -0.2983349561691284, "max": -0.17306485772132874, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02081734873354435, "min": -0.024195237085223198, "max": -0.018880417570471764, "count": 5 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.3330775797367096, "min": -0.35872793197631836, "max": -0.2640330195426941, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0879000024870038, "min": -0.5927384610359485, "max": 0.11727272786877373, "count": 5 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.4064000397920609, "min": -7.705599993467331, "max": 1.290000006556511, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0879000024870038, "min": -0.5927384610359485, "max": 0.11727272786877373, "count": 5 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.4064000397920609, "min": -7.705599993467331, "max": 1.290000006556511, "count": 5 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017824632406700402, "min": 0.012571493056990827, "max": 0.017824632406700402, "count": 2 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017824632406700402, "min": 0.012571493056990827, "max": 0.017824632406700402, "count": 2 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0025617227035885054, "min": 0.0025617227035885054, "max": 0.00809684682947894, "count": 2 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0025617227035885054, "min": 0.0025617227035885054, "max": 0.00809684682947894, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.00262952580039079, "min": 0.00262952580039079, "max": 0.008060800920551022, "count": 2 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.00262952580039079, "min": 0.00262952580039079, "max": 0.008060800920551022, "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": 0.20000000000000007, "max": 0.20000000000000007, "count": 2 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "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": "1718825817", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718825930" }, "total": 112.93022302100007, "count": 1, "self": 0.4340479590000541, "children": { "run_training.setup": { "total": 0.08535991799999465, "count": 1, "self": 0.08535991799999465 }, "TrainerController.start_learning": { "total": 112.41081514400003, "count": 1, "self": 0.07568648699270852, "children": { "TrainerController._reset_env": { "total": 2.624534799999765, "count": 2, "self": 2.624534799999765 }, "TrainerController.advance": { "total": 109.45053870500715, "count": 3453, "self": 0.08216692902124123, "children": { "env_step": { "total": 90.66438231600478, "count": 3453, "self": 69.19283895504668, "children": { "SubprocessEnvManager._take_step": { "total": 21.425694644980013, "count": 3453, "self": 0.5367119369525426, "children": { "TorchPolicy.evaluate": { "total": 20.88898270802747, "count": 6862, "self": 20.88898270802747 } } }, "workers": { "total": 0.0458487159780816, "count": 3453, "self": 0.0, "children": { "worker_root": { "total": 111.82617764100542, "count": 3453, "is_parallel": true, "self": 54.050345446024494, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032115050003085344, "count": 2, "is_parallel": true, "self": 0.000869087000410218, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023424179998983163, "count": 8, "is_parallel": true, "self": 0.0023424179998983163 } } }, "UnityEnvironment.step": { "total": 0.03800560600029712, "count": 1, "is_parallel": true, "self": 0.0011353880004207895, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0011964870000156225, "count": 1, "is_parallel": true, "self": 0.0011964870000156225 }, "communicator.exchange": { "total": 0.03233809099992868, "count": 1, "is_parallel": true, "self": 0.03233809099992868 }, "steps_from_proto": { "total": 0.0033356399999320274, "count": 2, "is_parallel": true, "self": 0.0005897940000068047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027458459999252227, "count": 8, "is_parallel": true, "self": 0.0027458459999252227 } } } } } } }, "steps_from_proto": { "total": 0.0019226939998588932, "count": 2, "is_parallel": true, "self": 0.00040570900000602705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015169849998528662, "count": 8, "is_parallel": true, "self": 0.0015169849998528662 } } }, "UnityEnvironment.step": { "total": 57.77390950098106, "count": 3452, "is_parallel": true, "self": 3.594404999980725, "children": { "UnityEnvironment._generate_step_input": { "total": 2.5842563200271798, "count": 3452, "is_parallel": true, "self": 2.5842563200271798 }, "communicator.exchange": { "total": 40.18668425298529, "count": 3452, "is_parallel": true, "self": 40.18668425298529 }, "steps_from_proto": { "total": 11.40856392798787, "count": 6904, "is_parallel": true, "self": 1.870944040982522, "children": { "_process_rank_one_or_two_observation": { "total": 9.537619887005349, "count": 27616, "is_parallel": true, "self": 9.537619887005349 } } } } } } } } } } }, "trainer_advance": { "total": 18.70398945998113, "count": 3453, "self": 0.598533009997027, "children": { "process_trajectory": { "total": 5.248613882984046, "count": 3453, "self": 5.248613882984046 }, "_update_policy": { "total": 12.856842567000058, "count": 2, "self": 7.492480968999189, "children": { "TorchPOCAOptimizer.update": { "total": 5.364361598000869, "count": 60, "self": 5.364361598000869 } } } } } } }, "trainer_threads": { "total": 9.270002010453027e-07, "count": 1, "self": 9.270002010453027e-07 }, "TrainerController._save_models": { "total": 0.2600542250002036, "count": 1, "self": 0.0026652270003069134, "children": { "RLTrainer._checkpoint": { "total": 0.2573889979998967, "count": 1, "self": 0.2573889979998967 } } } } } } }