{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.1925652027130127, "min": 2.0357096195220947, "max": 3.295631170272827, "count": 800 }, "SoccerTwos.Policy.Entropy.sum": { "value": 42798.875, "min": 29065.486328125, "max": 110619.3515625, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 504.55555555555554, "max": 999.0, "count": 800 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 12200.0, "max": 28524.0, "count": 800 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1199.9334636218261, "min": 1196.8453914730167, "max": 1204.9000747049904, "count": 65 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2399.8669272436523, "min": 2394.7921322129832, "max": 9632.44062650026, "count": 65 }, "SoccerTwos.Step.mean": { "value": 7999944.0, "min": 9278.0, "max": 7999944.0, "count": 800 }, "SoccerTwos.Step.sum": { "value": 7999944.0, "min": 9278.0, "max": 7999944.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.012500254437327385, "min": -0.06711050122976303, "max": 0.018256569281220436, "count": 800 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.12500254809856415, "min": -0.939547061920166, "max": 0.18256568908691406, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.012361116707324982, "min": -0.06710167974233627, "max": 0.013610780239105225, "count": 800 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.12361116707324982, "min": -0.9394006729125977, "max": 0.13610780239105225, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.4185714285288538, "max": 0.16814285516738892, "count": 800 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -5.8599999994039536, "max": 2.353999972343445, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.4185714285288538, "max": 0.16814285516738892, "count": 800 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -5.8599999994039536, "max": 2.353999972343445, "count": 800 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 800 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013426195655483752, "min": 0.010731164743386519, "max": 0.022484100555690625, "count": 365 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013426195655483752, "min": 0.010731164743386519, "max": 0.022484100555690625, "count": 365 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 2.2728424664819612e-05, "min": 3.622488022510713e-10, "max": 0.04969244154425117, "count": 365 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 2.2728424664819612e-05, "min": 3.622488022510713e-10, "max": 0.04969244154425117, "count": 365 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 3.371514682536751e-05, "min": 4.852258724448906e-10, "max": 0.053099278115799585, "count": 365 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 3.371514682536751e-05, "min": 4.852258724448906e-10, "max": 0.053099278115799585, "count": 365 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 365 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 365 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 365 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 365 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 365 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 365 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683147653", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\kingk\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1683159499" }, "total": 11846.9075292, "count": 1, "self": 4.130778700000519, "children": { "run_training.setup": { "total": 0.06870520000000013, "count": 1, "self": 0.06870520000000013 }, "TrainerController.start_learning": { "total": 11842.7080453, "count": 1, "self": 8.680754000451998, "children": { "TrainerController._reset_env": { "total": 5.516737000000538, "count": 40, "self": 5.516737000000538 }, "TrainerController.advance": { "total": 11828.357280399548, "count": 520568, "self": 9.474384999253743, "children": { "env_step": { "total": 9001.134529999916, "count": 520568, "self": 5258.721903999822, "children": { "SubprocessEnvManager._take_step": { "total": 3736.4428117002003, "count": 520568, "self": 59.703648000168414, "children": { "TorchPolicy.evaluate": { "total": 3676.739163700032, "count": 1034124, "self": 3676.739163700032 } } }, "workers": { "total": 5.969814299893104, "count": 520567, "self": 0.0, "children": { "worker_root": { "total": 11826.65870089953, "count": 520567, "is_parallel": true, "self": 7688.050879899954, "children": { "steps_from_proto": { "total": 0.0885296000048661, "count": 80, "is_parallel": true, "self": 0.0183252000139964, "children": { "_process_rank_one_or_two_observation": { "total": 0.07020439999086969, "count": 320, "is_parallel": true, "self": 0.07020439999086969 } } }, "UnityEnvironment.step": { "total": 4138.519291399571, "count": 520567, "is_parallel": true, "self": 221.24659419827094, "children": { "UnityEnvironment._generate_step_input": { "total": 314.96789329995363, "count": 520567, "is_parallel": true, "self": 314.96789329995363 }, "communicator.exchange": { "total": 2890.5178727002058, "count": 520567, "is_parallel": true, "self": 2890.5178727002058 }, "steps_from_proto": { "total": 711.7869312011401, "count": 1041134, "is_parallel": true, "self": 149.8315113017693, "children": { "_process_rank_one_or_two_observation": { "total": 561.9554198993708, "count": 4164536, "is_parallel": true, "self": 561.9554198993708 } } } } } } } } } } }, "trainer_advance": { "total": 2817.748365400379, "count": 520567, "self": 66.07151470030749, "children": { "process_trajectory": { "total": 947.8506300000706, "count": 520567, "self": 944.8551793000722, "children": { "RLTrainer._checkpoint": { "total": 2.9954506999984005, "count": 16, "self": 2.9954506999984005 } } }, "_update_policy": { "total": 1803.8262207000012, "count": 366, "self": 1129.6175799999464, "children": { "TorchPOCAOptimizer.update": { "total": 674.2086407000547, "count": 10980, "self": 674.2086407000547 } } } } } } }, "trainer_threads": { "total": 1.0999992809956893e-06, "count": 1, "self": 1.0999992809956893e-06 }, "TrainerController._save_models": { "total": 0.15327280000019528, "count": 1, "self": 0.012785599999915576, "children": { "RLTrainer._checkpoint": { "total": 0.1404872000002797, "count": 1, "self": 0.1404872000002797 } } } } } } }