{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45875608921051025, "min": 0.45875608921051025, "max": 0.8841205835342407, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 13733.322265625, "min": 9760.69140625, "max": 26327.4453125, "count": 17 }, "Pyramids.Step.mean": { "value": 989917.0, "min": 509960.0, "max": 989917.0, "count": 17 }, "Pyramids.Step.sum": { "value": 989917.0, "min": 509960.0, "max": 989917.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6127039194107056, "min": 0.18280494213104248, "max": 0.6332113146781921, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.55709838867188, "min": 15.35561466217041, "max": 177.932373046875, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02891494892537594, "min": -0.04961053654551506, "max": -0.00021673558512702584, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.096185684204102, "min": -12.799518585205078, "max": -0.057218194007873535, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 323.5274725274725, "min": 292.1212121212121, "max": 586.5686274509804, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29441.0, "min": 5418.0, "max": 31872.0, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6325120695017197, "min": 1.0018654112111438, "max": 1.6619463731947632, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.5585983246565, "min": 19.271000012755394, "max": 163.07839775830507, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6325120695017197, "min": 1.0018654112111438, "max": 1.6619463731947632, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.5585983246565, "min": 19.271000012755394, "max": 163.07839775830507, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024871541401288205, "min": 0.023012268349482452, "max": 0.08642986296147753, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2633102675172267, "min": 0.7473170382436365, "max": 4.4943528739968315, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07094842168763059, "min": 0.06475485880881289, "max": 0.07261670442537815, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9932779036268283, "min": 0.2801995384021817, "max": 1.0809911646744392, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013959071398684976, "min": 0.009420607385436597, "max": 0.014885757200312943, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19542699958158966, "min": 0.03768242954174639, "max": 0.21406570552305004, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.537704630321429e-06, "min": 7.537704630321429e-06, "max": 0.00014843060052315, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001055278648245, "min": 0.0001055278648245, "max": 0.0020021732326092, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251253571428569, "min": 0.10251253571428569, "max": 0.14947685, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351754999999997, "min": 0.5979074, "max": 2.1673907999999997, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002610023178571428, "min": 0.0002610023178571428, "max": 0.004952737314999999, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036540324499999997, "min": 0.0036540324499999997, "max": 0.06682234092, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007446191273629665, "min": 0.007446191273629665, "max": 0.015518076717853546, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10424667596817017, "min": 0.062072306871414185, "max": 0.19433340430259705, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1791088488", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/content/mlagents-env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1791089737" }, "total": 1248.2365499080001, "count": 1, "self": 0.5873378240003149, "children": { "run_training.setup": { "total": 0.023611859000084223, "count": 1, "self": 0.023611859000084223 }, "TrainerController.start_learning": { "total": 1247.6256002249997, "count": 1, "self": 0.9642267730664571, "children": { "TrainerController._reset_env": { "total": 2.0792862130001595, "count": 1, "self": 2.0792862130001595 }, "TrainerController.advance": { "total": 1244.5345832119338, "count": 32288, "self": 0.9146226068319265, "children": { "env_step": { "total": 882.3119577690595, "count": 32288, "self": 823.9560867890909, "children": { "SubprocessEnvManager._take_step": { "total": 57.710266524011786, "count": 32288, "self": 2.3266430120343102, "children": { "TorchPolicy.evaluate": { "total": 55.383623511977476, "count": 31303, "self": 55.383623511977476 } } }, "workers": { "total": 0.6456044559567999, "count": 32288, "self": 0.0, "children": { "worker_root": { "total": 1245.11994504301, "count": 32288, "is_parallel": true, "self": 489.37081120898347, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020851700001003337, "count": 1, "is_parallel": true, "self": 0.0007920400003058603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012931299997944734, "count": 8, "is_parallel": true, "self": 0.0012931299997944734 } } }, "UnityEnvironment.step": { "total": 0.055853277999631246, "count": 1, "is_parallel": true, "self": 0.0005147999995642749, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004479089998312702, "count": 1, "is_parallel": true, "self": 0.0004479089998312702 }, "communicator.exchange": { "total": 0.05315362900000764, "count": 1, "is_parallel": true, "self": 0.05315362900000764 }, "steps_from_proto": { "total": 0.00173694000022806, "count": 1, "is_parallel": true, "self": 0.0003084300001319207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014285100000961393, "count": 8, "is_parallel": true, "self": 0.0014285100000961393 } } } } } } }, "UnityEnvironment.step": { "total": 755.7491338340265, "count": 32287, "is_parallel": true, "self": 17.781315220983743, "children": { "UnityEnvironment._generate_step_input": { "total": 12.388142433068879, "count": 32287, "is_parallel": true, "self": 12.388142433068879 }, "communicator.exchange": { "total": 673.3742121060768, "count": 32287, "is_parallel": true, "self": 673.3742121060768 }, "steps_from_proto": { "total": 52.20546407389702, "count": 32287, "is_parallel": true, "self": 11.738880226754645, "children": { "_process_rank_one_or_two_observation": { "total": 40.466583847142374, "count": 258296, "is_parallel": true, "self": 40.466583847142374 } } } } } } } } } } }, "trainer_advance": { "total": 361.3080028360423, "count": 32288, "self": 2.05601445694856, "children": { "process_trajectory": { "total": 57.555018019093495, "count": 32288, "self": 57.40726597409321, "children": { "RLTrainer._checkpoint": { "total": 0.1477520450002885, "count": 2, "self": 0.1477520450002885 } } }, "_update_policy": { "total": 301.69697036000025, "count": 236, "self": 124.14156648702419, "children": { "TorchPPOOptimizer.update": { "total": 177.55540387297606, "count": 11361, "self": 177.55540387297606 } } } } } } }, "trainer_threads": { "total": 9.199993655784056e-07, "count": 1, "self": 9.199993655784056e-07 }, "TrainerController._save_models": { "total": 0.04750310700001137, "count": 1, "self": 0.0009119100004681968, "children": { "RLTrainer._checkpoint": { "total": 0.04659119699954317, "count": 1, "self": 0.04659119699954317 } } } } } } }