{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.207034111022949, "min": 3.195733070373535, "max": 3.237135887145996, "count": 74 }, "SoccerTwos.Policy.Entropy.sum": { "value": 63114.4296875, "min": 24813.296875, "max": 103490.671875, "count": 74 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 722.0, "min": 466.0, "max": 999.0, "count": 74 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17328.0, "min": 11988.0, "max": 31448.0, "count": 74 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.9095325253534, "min": 1197.2513086528097, "max": 1207.6485228203383, "count": 51 }, "SoccerTwos.Self-play.ELO.sum": { "value": 9639.276260202827, "min": 2394.5026173056194, "max": 12076.485228203383, "count": 51 }, "SoccerTwos.Step.mean": { "value": 999780.0, "min": 259079.0, "max": 999780.0, "count": 75 }, "SoccerTwos.Step.sum": { "value": 999780.0, "min": 259079.0, "max": 999780.0, "count": 75 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01595696620643139, "min": -0.023637687787413597, "max": 0.008386930450797081, "count": 75 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.2074405550956726, "min": -0.28365224599838257, "max": 0.09589813649654388, "count": 75 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01624440588057041, "min": -0.024123603478074074, "max": 0.007923462428152561, "count": 75 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2111772745847702, "min": -0.2894832491874695, "max": 0.0972113162279129, "count": 75 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 75 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 75 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.42859999950115496, "min": -0.42859999950115496, "max": 0.32130000554025173, "count": 75 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.571799993515015, "min": -5.571799993515015, "max": 5.140800088644028, "count": 75 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.42859999950115496, "min": -0.42859999950115496, "max": 0.32130000554025173, "count": 75 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.571799993515015, "min": -5.571799993515015, "max": 5.140800088644028, "count": 75 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 75 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 75 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01614117485781511, "min": 0.012441317781728382, "max": 0.022755093033225017, "count": 34 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01614117485781511, "min": 0.012441317781728382, "max": 0.022755093033225017, "count": 34 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003393122786656022, "min": 8.370173736693686e-06, "max": 0.0043563801717634, "count": 34 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003393122786656022, "min": 8.370173736693686e-06, "max": 0.0043563801717634, "count": 34 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003496897577618559, "min": 8.588571442184426e-06, "max": 0.0043817395266766345, "count": 34 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003496897577618559, "min": 8.588571442184426e-06, "max": 0.0043817395266766345, "count": 34 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 34 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 34 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 34 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 34 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 34 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717146329", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\User\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --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+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717149069" }, "total": 2739.635941299959, "count": 1, "self": 8.018365099909715, "children": { "run_training.setup": { "total": 20.091053000069223, "count": 1, "self": 20.091053000069223 }, "TrainerController.start_learning": { "total": 2711.52652319998, "count": 1, "self": 1.5683462915476412, "children": { "TrainerController._reset_env": { "total": 33.86788459983654, "count": 5, "self": 33.86788459983654 }, "TrainerController.advance": { "total": 2675.8766679086257, "count": 48750, "self": 1.6080809925915673, "children": { "env_step": { "total": 1078.9752967073582, "count": 48750, "self": 794.534522132948, "children": { "SubprocessEnvManager._take_step": { "total": 283.46425178449135, "count": 48750, "self": 9.413497863337398, "children": { "TorchPolicy.evaluate": { "total": 274.05075392115396, "count": 96842, "self": 274.05075392115396 } } }, "workers": { "total": 0.9765227899188176, "count": 48750, "self": 0.0, "children": { "worker_root": { "total": 2680.837356209755, "count": 48750, "is_parallel": true, "self": 2072.1351201153593, "children": { "steps_from_proto": { "total": 0.01413460006006062, "count": 10, "is_parallel": true, "self": 0.0029638997511938214, "children": { "_process_rank_one_or_two_observation": { "total": 0.011170700308866799, "count": 40, "is_parallel": true, "self": 0.011170700308866799 } } }, "UnityEnvironment.step": { "total": 608.6881014943356, "count": 48750, "is_parallel": true, "self": 33.7895703825634, "children": { "UnityEnvironment._generate_step_input": { "total": 26.27174610516522, "count": 48750, "is_parallel": true, "self": 26.27174610516522 }, "communicator.exchange": { "total": 446.7445906009525, "count": 48750, "is_parallel": true, "self": 446.7445906009525 }, "steps_from_proto": { "total": 101.88219440565445, "count": 97500, "is_parallel": true, "self": 20.896080320933834, "children": { "_process_rank_one_or_two_observation": { "total": 80.98611408472061, "count": 390000, "is_parallel": true, "self": 80.98611408472061 } } } } } } } } } } }, "trainer_advance": { "total": 1595.293290208676, "count": 48750, "self": 11.13482260541059, "children": { "process_trajectory": { "total": 231.44681030325592, "count": 48750, "self": 230.99146780313458, "children": { "RLTrainer._checkpoint": { "total": 0.4553425001213327, "count": 2, "self": 0.4553425001213327 } } }, "_update_policy": { "total": 1352.7116573000094, "count": 34, "self": 143.39030400139745, "children": { "TorchPOCAOptimizer.update": { "total": 1209.321353298612, "count": 1038, "self": 1209.321353298612 } } } } } } }, "trainer_threads": { "total": 1.200009137392044e-06, "count": 1, "self": 1.200009137392044e-06 }, "TrainerController._save_models": { "total": 0.2136231999611482, "count": 1, "self": 0.011383900069631636, "children": { "RLTrainer._checkpoint": { "total": 0.20223929989151657, "count": 1, "self": 0.20223929989151657 } } } } } } }