{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.207277536392212, "min": 3.1662485599517822, "max": 3.295755386352539, "count": 60 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55011.22265625, "min": 15025.4150390625, "max": 130494.0, "count": 60 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 862.2, "min": 520.875, "max": 999.0, "count": 60 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 17244.0, "min": 16668.0, "max": 23536.0, "count": 60 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1191.2103618060098, "min": 1190.4527156990193, "max": 1202.670384445195, "count": 41 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2382.4207236120196, "min": 2380.9054313980387, "max": 12009.529092161078, "count": 41 }, "SoccerTwos.Step.mean": { "value": 599156.0, "min": 9786.0, "max": 599156.0, "count": 60 }, "SoccerTwos.Step.sum": { "value": 599156.0, "min": 9786.0, "max": 599156.0, "count": 60 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.00412715133279562, "min": -0.0034613609313964844, "max": 0.019683940336108208, "count": 60 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.045398663729429245, "min": -0.04153633117675781, "max": 0.3149021863937378, "count": 60 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.00709341187030077, "min": -0.006019020918756723, "max": 0.01960267499089241, "count": 60 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.07802753150463104, "min": -0.06019020825624466, "max": 0.31359928846359253, "count": 60 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 60 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 60 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.18181818181818182, "min": -0.35467692521902233, "max": 0.15280000368754068, "count": 60 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.0, "min": -5.069599986076355, "max": 1.8336000442504883, "count": 60 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.18181818181818182, "min": -0.35467692521902233, "max": 0.15280000368754068, "count": 60 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.0, "min": -5.069599986076355, "max": 1.8336000442504883, "count": 60 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015370510941526543, "min": 0.011347853918092217, "max": 0.02013839826104231, "count": 27 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015370510941526543, "min": 0.011347853918092217, "max": 0.02013839826104231, "count": 27 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0007796116076254596, "min": 7.393880999491861e-06, "max": 0.005053716711699963, "count": 27 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0007796116076254596, "min": 7.393880999491861e-06, "max": 0.005053716711699963, "count": 27 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.000957965963849953, "min": 7.547470507536976e-06, "max": 0.00475320645297567, "count": 27 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.000957965963849953, "min": 7.547470507536976e-06, "max": 0.00475320645297567, "count": 27 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 27 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 27 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 27 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 27 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 27 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 27 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710073030", "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": "\\\\?\\D:\\Xavier\\APPLICATION\\Anaconda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1710074337" }, "total": 1306.5810825999997, "count": 1, "self": 0.7605820999979187, "children": { "run_training.setup": { "total": 0.08995730000060576, "count": 1, "self": 0.08995730000060576 }, "TrainerController.start_learning": { "total": 1305.7305432000012, "count": 1, "self": 0.8318942999721912, "children": { "TrainerController._reset_env": { "total": 6.5468208999973285, "count": 3, "self": 6.5468208999973285 }, "TrainerController.advance": { "total": 1298.2392317000304, "count": 38935, "self": 0.8918339002484572, "children": { "env_step": { "total": 604.5544607999454, "count": 38935, "self": 462.90601369955766, "children": { "SubprocessEnvManager._take_step": { "total": 141.13036120018478, "count": 38935, "self": 4.407879299942579, "children": { "TorchPolicy.evaluate": { "total": 136.7224819002422, "count": 77326, "self": 136.7224819002422 } } }, "workers": { "total": 0.5180859002030047, "count": 38935, "self": 0.0, "children": { "worker_root": { "total": 1298.7086661998874, "count": 38935, "is_parallel": true, "self": 938.8576081997708, "children": { "steps_from_proto": { "total": 0.004592600000250968, "count": 6, "is_parallel": true, "self": 0.0009451999976590741, "children": { "_process_rank_one_or_two_observation": { "total": 0.003647400002591894, "count": 24, "is_parallel": true, "self": 0.003647400002591894 } } }, "UnityEnvironment.step": { "total": 359.84646540011636, "count": 38935, "is_parallel": true, "self": 18.731217000082324, "children": { "UnityEnvironment._generate_step_input": { "total": 17.919321899855277, "count": 38935, "is_parallel": true, "self": 17.919321899855277 }, "communicator.exchange": { "total": 260.8434526000656, "count": 38935, "is_parallel": true, "self": 260.8434526000656 }, "steps_from_proto": { "total": 62.35247390011318, "count": 77870, "is_parallel": true, "self": 12.745539801178893, "children": { "_process_rank_one_or_two_observation": { "total": 49.60693409893429, "count": 311480, "is_parallel": true, "self": 49.60693409893429 } } } } } } } } } } }, "trainer_advance": { "total": 692.7929369998365, "count": 38935, "self": 6.191813299639762, "children": { "process_trajectory": { "total": 103.77766660019734, "count": 38935, "self": 103.61519650019727, "children": { "RLTrainer._checkpoint": { "total": 0.16247010000006412, "count": 1, "self": 0.16247010000006412 } } }, "_update_policy": { "total": 582.8234570999994, "count": 27, "self": 80.05594600002223, "children": { "TorchPOCAOptimizer.update": { "total": 502.7675110999771, "count": 810, "self": 502.7675110999771 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.11259530000097584, "count": 1, "self": 0.0070030000006227056, "children": { "RLTrainer._checkpoint": { "total": 0.10559230000035313, "count": 1, "self": 0.10559230000035313 } } } } } } }