{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5505513548851013, "min": 0.5505513548851013, "max": 1.4167014360427856, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16384.408203125, "min": 16384.408203125, "max": 42977.0546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1219722181558609, "min": -0.10626282542943954, "max": 0.20608457922935486, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 30.73699951171875, "min": -25.60934066772461, "max": 52.345481872558594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07707514613866806, "min": -0.06596412509679794, "max": 0.5060542821884155, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 19.422937393188477, "min": -16.7548885345459, "max": 119.93486022949219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07018037533584993, "min": 0.06451662967231936, "max": 0.07363603323465213, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.982525254701899, "min": 0.4848458311492417, "max": 1.104540498519782, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008825935397214104, "min": 5.982214327082022e-05, "max": 0.012629955665404145, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.12356309556099744, "min": 0.0007776878625206629, "max": 0.16009759975956211, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.646476022635719e-06, "min": 7.646476022635719e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010705066431690006, "min": 0.00010705066431690006, "max": 0.0032242867252377993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254879285714287, "min": 0.10254879285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356831, "min": 1.3691136000000002, "max": 2.3081813000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026462440642857155, "min": 0.00026462440642857155, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037047416900000017, "min": 0.0037047416900000017, "max": 0.10748874378000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015060283243656158, "min": 0.015060283243656158, "max": 0.5361228585243225, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21084396541118622, "min": 0.21084396541118622, "max": 3.7528598308563232, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 679.0227272727273, "min": 613.2340425531914, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29877.0, "min": 15984.0, "max": 32653.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5211860111286474, "min": -1.0000000521540642, "max": 0.8759574097521762, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 22.410998478531837, "min": -32.000001668930054, "max": 41.16999825835228, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5211860111286474, "min": -1.0000000521540642, "max": 0.8759574097521762, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 22.410998478531837, "min": -32.000001668930054, "max": 41.16999825835228, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1064517994811975, "min": 0.09769848065990756, "max": 11.091340923681855, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.577427377691492, "min": 4.549132539192215, "max": 177.46145477890968, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687873896", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687875893" }, "total": 1997.097146092, "count": 1, "self": 1.2835085090000575, "children": { "run_training.setup": { "total": 0.04179961799991361, "count": 1, "self": 0.04179961799991361 }, "TrainerController.start_learning": { "total": 1995.771837965, "count": 1, "self": 1.3094397830095659, "children": { "TrainerController._reset_env": { "total": 4.965006517999882, "count": 1, "self": 4.965006517999882 }, "TrainerController.advance": { "total": 1989.3584154219902, "count": 63222, "self": 1.3741559219852206, "children": { "env_step": { "total": 1355.3463093400565, "count": 63222, "self": 1246.398699968051, "children": { "SubprocessEnvManager._take_step": { "total": 108.15227151904355, "count": 63222, "self": 4.671855593092005, "children": { "TorchPolicy.evaluate": { "total": 103.48041592595155, "count": 62579, "self": 103.48041592595155 } } }, "workers": { "total": 0.7953378529618931, "count": 63222, "self": 0.0, "children": { "worker_root": { "total": 1990.9530861110247, "count": 63222, "is_parallel": true, "self": 855.5327435499566, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018385179996585066, "count": 1, "is_parallel": true, "self": 0.0005915100000493112, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012470079996091954, "count": 8, "is_parallel": true, "self": 0.0012470079996091954 } } }, "UnityEnvironment.step": { "total": 0.10106155199991917, "count": 1, "is_parallel": true, "self": 0.0006685339994874084, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005184390001886641, "count": 1, "is_parallel": true, "self": 0.0005184390001886641 }, "communicator.exchange": { "total": 0.09784881099994891, "count": 1, "is_parallel": true, "self": 0.09784881099994891 }, "steps_from_proto": { "total": 0.0020257680002941925, "count": 1, "is_parallel": true, "self": 0.00039084199988792534, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016349260004062671, "count": 8, "is_parallel": true, "self": 0.0016349260004062671 } } } } } } }, "UnityEnvironment.step": { "total": 1135.420342561068, "count": 63221, "is_parallel": true, "self": 32.729480024042914, "children": { "UnityEnvironment._generate_step_input": { "total": 23.11452285296855, "count": 63221, "is_parallel": true, "self": 23.11452285296855 }, "communicator.exchange": { "total": 980.3362975710629, "count": 63221, "is_parallel": true, "self": 980.3362975710629 }, "steps_from_proto": { "total": 99.2400421129937, "count": 63221, "is_parallel": true, "self": 19.226253153165544, "children": { "_process_rank_one_or_two_observation": { "total": 80.01378895982816, "count": 505768, "is_parallel": true, "self": 80.01378895982816 } } } } } } } } } } }, "trainer_advance": { "total": 632.6379501599486, "count": 63222, "self": 2.438642733942288, "children": { "process_trajectory": { "total": 105.6273308300074, "count": 63222, "self": 105.37466987700782, "children": { "RLTrainer._checkpoint": { "total": 0.2526609529995767, "count": 2, "self": 0.2526609529995767 } } }, "_update_policy": { "total": 524.5719765959989, "count": 433, "self": 336.15857428299796, "children": { "TorchPPOOptimizer.update": { "total": 188.41340231300092, "count": 22818, "self": 188.41340231300092 } } } } } } }, "trainer_threads": { "total": 1.4550005289493129e-06, "count": 1, "self": 1.4550005289493129e-06 }, "TrainerController._save_models": { "total": 0.13897478699982457, "count": 1, "self": 0.0018483389994798927, "children": { "RLTrainer._checkpoint": { "total": 0.13712644800034468, "count": 1, "self": 0.13712644800034468 } } } } } } }