{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6669374704360962, "min": 1.6359543800354004, "max": 1.6686762571334839, "count": 7 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33285.40625, "min": 28373.9921875, "max": 35656.47265625, "count": 7 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.27777777777777, "min": 56.20238095238095, "max": 69.27777777777777, "count": 7 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19952.0, "min": 16200.0, "max": 20212.0, "count": 7 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1539.4471772250445, "min": 1527.7409143925404, "max": 1545.935715339572, "count": 7 }, "SoccerTwos.Self-play.ELO.sum": { "value": 221680.3935204064, "min": 210247.2572861818, "max": 258303.83899147165, "count": 7 }, "SoccerTwos.Step.mean": { "value": 7759836.0, "min": 7699856.0, "max": 7759836.0, "count": 7 }, "SoccerTwos.Step.sum": { "value": 7759836.0, "min": 7699856.0, "max": 7759836.0, "count": 7 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02039300464093685, "min": -0.06732017546892166, "max": 0.006477044429630041, "count": 7 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.9161996841430664, "min": -10.462895393371582, "max": 0.8679239749908447, "count": 7 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.018799273297190666, "min": -0.06896685063838959, "max": 0.014638231135904789, "count": 7 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.68829607963562, "min": -10.482961654663086, "max": 1.9615229368209839, "count": 7 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 7 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 7 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.017475523315109574, "min": -0.14296273452154598, "max": 0.18005912183965528, "count": 7 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.498999834060669, "min": -23.017000257968903, "max": 28.629400372505188, "count": 7 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.017475523315109574, "min": -0.14296273452154598, "max": 0.18005912183965528, "count": 7 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.498999834060669, "min": -23.017000257968903, "max": 28.629400372505188, "count": 7 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016602384811267256, "min": 0.014415907952934504, "max": 0.016602384811267256, "count": 3 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016602384811267256, "min": 0.014415907952934504, "max": 0.016602384811267256, "count": 3 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09950689375400543, "min": 0.09836041977008184, "max": 0.10183645983537039, "count": 3 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09950689375400543, "min": 0.09836041977008184, "max": 0.10183645983537039, "count": 3 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1016091840962569, "min": 0.10012397617101669, "max": 0.10352428729335467, "count": 3 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1016091840962569, "min": 0.10012397617101669, "max": 0.10352428729335467, "count": 3 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 3 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0005000000000000001, "min": 0.0005000000000000001, "max": 0.0005000000000000001, "count": 3 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 3 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 3 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 3 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706602397", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706602573" }, "total": 176.3850563119995, "count": 1, "self": 0.6095307819996378, "children": { "run_training.setup": { "total": 0.06312701000206289, "count": 1, "self": 0.06312701000206289 }, "TrainerController.start_learning": { "total": 175.7123985199978, "count": 1, "self": 0.1427209370849596, "children": { "TrainerController._reset_env": { "total": 3.9993831899955694, "count": 2, "self": 3.9993831899955694 }, "TrainerController.advance": { "total": 171.57022046191923, "count": 4856, "self": 0.14406386593691423, "children": { "env_step": { "total": 134.875863562007, "count": 4856, "self": 104.80080308114339, "children": { "SubprocessEnvManager._take_step": { "total": 29.993070571970748, "count": 4856, "self": 0.7589429501349514, "children": { "TorchPolicy.evaluate": { "total": 29.234127621835796, "count": 8830, "self": 29.234127621835796 } } }, "workers": { "total": 0.08198990889286506, "count": 4855, "self": 0.0, "children": { "worker_root": { "total": 175.3619194520361, "count": 4855, "is_parallel": true, "self": 87.06817251295797, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002859461001207819, "count": 2, "is_parallel": true, "self": 0.0007165480019466486, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021429129992611706, "count": 8, "is_parallel": true, "self": 0.0021429129992611706 } } }, "UnityEnvironment.step": { "total": 0.042817464000108885, "count": 1, "is_parallel": true, "self": 0.0012375180012895726, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009868800007097889, "count": 1, "is_parallel": true, "self": 0.0009868800007097889 }, "communicator.exchange": { "total": 0.03684870999859413, "count": 1, "is_parallel": true, "self": 0.03684870999859413 }, "steps_from_proto": { "total": 0.003744355999515392, "count": 2, "is_parallel": true, "self": 0.0006717589967593085, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030725970027560834, "count": 8, "is_parallel": true, "self": 0.0030725970027560834 } } } } } } }, "steps_from_proto": { "total": 0.0020243369981471915, "count": 2, "is_parallel": true, "self": 0.00053981399469194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014845230034552515, "count": 8, "is_parallel": true, "self": 0.0014845230034552515 } } }, "UnityEnvironment.step": { "total": 88.29172260207997, "count": 4854, "is_parallel": true, "self": 5.486264983432193, "children": { "UnityEnvironment._generate_step_input": { "total": 3.4638925718209066, "count": 4854, "is_parallel": true, "self": 3.4638925718209066 }, "communicator.exchange": { "total": 62.658482434926555, "count": 4854, "is_parallel": true, "self": 62.658482434926555 }, "steps_from_proto": { "total": 16.683082611900318, "count": 9708, "is_parallel": true, "self": 2.7760117232974153, "children": { "_process_rank_one_or_two_observation": { "total": 13.907070888602902, "count": 38832, "is_parallel": true, "self": 13.907070888602902 } } } } } } } } } } }, "trainer_advance": { "total": 36.55029303397532, "count": 4855, "self": 1.0077057810412953, "children": { "process_trajectory": { "total": 18.079415830929065, "count": 4855, "self": 18.079415830929065 }, "_update_policy": { "total": 17.46317142200496, "count": 3, "self": 10.25110586601295, "children": { "TorchPOCAOptimizer.update": { "total": 7.212065555992012, "count": 90, "self": 7.212065555992012 } } } } } } }, "trainer_threads": { "total": 1.2669988791458309e-06, "count": 1, "self": 1.2669988791458309e-06 }, "TrainerController._save_models": { "total": 7.266399916261435e-05, "count": 1, "self": 5.557499753194861e-05, "children": { "RLTrainer._checkpoint": { "total": 1.7089001630665734e-05, "count": 1, "self": 1.7089001630665734e-05 } } } } } } }