{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5850025415420532, "min": 0.5789114832878113, "max": 1.0183769464492798, "count": 31 }, "Pyramids.Policy.Entropy.sum": { "value": 17550.076171875, "min": 17487.7578125, "max": 30893.484375, "count": 31 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 89984.0, "max": 989935.0, "count": 31 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 89984.0, "max": 989935.0, "count": 31 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.307701051235199, "min": -0.1163356751203537, "max": 0.3234853148460388, "count": 31 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 79.69457244873047, "min": -27.920562744140625, "max": 84.4296646118164, "count": 31 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009780224412679672, "min": 0.009113227017223835, "max": 0.15215526521205902, "count": 31 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.533078193664551, "min": 2.3614554405212402, "max": 35.75648880004883, "count": 31 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0702149541293776, "min": 0.06466804394383366, "max": 0.07124964130714515, "count": 31 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0532243119406641, "min": 0.47301760811697235, "max": 1.0625258805133246, "count": 31 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01172638674056632, "min": 0.0002597783872054222, "max": 0.014854764785836564, "count": 31 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17589580110849481, "min": 0.0018184487104379555, "max": 0.20796670700171188, "count": 31 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5016774994733325e-06, "min": 7.5016774994733325e-06, "max": 0.0002770642362166857, "count": 31 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011252516249209999, "min": 0.00011252516249209999, "max": 0.0030259313913563, "count": 31 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025005266666667, "min": 0.1025005266666667, "max": 0.19235474285714282, "count": 31 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375079000000005, "min": 1.3269120000000003, "max": 2.3168816000000003, "count": 31 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025980261399999994, "min": 0.00025980261399999994, "max": 0.009236238811428571, "count": 31 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038970392099999993, "min": 0.0038970392099999993, "max": 0.10089350562999999, "count": 31 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012468215078115463, "min": 0.012468215078115463, "max": 0.08149807900190353, "count": 31 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18702322244644165, "min": 0.18042507767677307, "max": 0.5704865455627441, "count": 31 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 565.3461538461538, "min": 480.61290322580646, "max": 999.0, "count": 31 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29398.0, "min": 15984.0, "max": 32839.0, "count": 31 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0499038100242615, "min": -1.0000000521540642, "max": 1.3903064249503998, "count": 31 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 54.5949981212616, "min": -32.000001668930054, "max": 86.19899834692478, "count": 31 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0499038100242615, "min": -1.0000000521540642, "max": 1.3903064249503998, "count": 31 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 54.5949981212616, "min": -32.000001668930054, "max": 86.19899834692478, "count": 31 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07296601733315373, "min": 0.06647319333334904, "max": 0.9577913281973451, "count": 31 }, "Pyramids.Policy.RndReward.sum": { "value": 3.794232901323994, "min": 3.794232901323994, "max": 21.079867471009493, "count": 31 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 31 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 31 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690132648", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --resume --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": "1690134799" }, "total": 2151.175003026, "count": 1, "self": 0.5292534260001958, "children": { "run_training.setup": { "total": 0.033243087000300875, "count": 1, "self": 0.033243087000300875 }, "TrainerController.start_learning": { "total": 2150.6125065129995, "count": 1, "self": 1.6569540658933875, "children": { "TrainerController._reset_env": { "total": 4.179131510999923, "count": 1, "self": 4.179131510999923 }, "TrainerController.advance": { "total": 2144.660074440106, "count": 59553, "self": 1.6072343531473052, "children": { "env_step": { "total": 1476.6745108260252, "count": 59553, "self": 1355.137353665063, "children": { "SubprocessEnvManager._take_step": { "total": 120.54106604098979, "count": 59553, "self": 5.232810973906453, "children": { "TorchPolicy.evaluate": { "total": 115.30825506708334, "count": 58795, "self": 115.30825506708334 } } }, "workers": { "total": 0.9960911199723341, "count": 59553, "self": 0.0, "children": { "worker_root": { "total": 2144.659062445032, "count": 59553, "is_parallel": true, "self": 916.1342235529692, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018752639998638188, "count": 1, "is_parallel": true, "self": 0.0006325820004349225, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012426819994288962, "count": 8, "is_parallel": true, "self": 0.0012426819994288962 } } }, "UnityEnvironment.step": { "total": 0.06601722200002769, "count": 1, "is_parallel": true, "self": 0.000684134999573871, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005233780002527055, "count": 1, "is_parallel": true, "self": 0.0005233780002527055 }, "communicator.exchange": { "total": 0.06281779300024937, "count": 1, "is_parallel": true, "self": 0.06281779300024937 }, "steps_from_proto": { "total": 0.0019919159999517433, "count": 1, "is_parallel": true, "self": 0.00040145000093616545, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015904659990155778, "count": 8, "is_parallel": true, "self": 0.0015904659990155778 } } } } } } }, "UnityEnvironment.step": { "total": 1228.5248388920627, "count": 59552, "is_parallel": true, "self": 35.466716293954505, "children": { "UnityEnvironment._generate_step_input": { "total": 24.687534532075915, "count": 59552, "is_parallel": true, "self": 24.687534532075915 }, "communicator.exchange": { "total": 1059.2312950999594, "count": 59552, "is_parallel": true, "self": 1059.2312950999594 }, "steps_from_proto": { "total": 109.13929296607284, "count": 59552, "is_parallel": true, "self": 22.719013534012902, "children": { "_process_rank_one_or_two_observation": { "total": 86.42027943205994, "count": 476416, "is_parallel": true, "self": 86.42027943205994 } } } } } } } } } } }, "trainer_advance": { "total": 666.3783292609337, "count": 59553, "self": 2.9184164598596, "children": { "process_trajectory": { "total": 116.02130726207088, "count": 59553, "self": 115.72638736107046, "children": { "RLTrainer._checkpoint": { "total": 0.2949199010004122, "count": 2, "self": 0.2949199010004122 } } }, "_update_policy": { "total": 547.4386055390032, "count": 410, "self": 358.882889516035, "children": { "TorchPPOOptimizer.update": { "total": 188.55571602296823, "count": 21408, "self": 188.55571602296823 } } } } } } }, "trainer_threads": { "total": 8.280003385152668e-07, "count": 1, "self": 8.280003385152668e-07 }, "TrainerController._save_models": { "total": 0.11634566799966706, "count": 1, "self": 0.0018633340005180798, "children": { "RLTrainer._checkpoint": { "total": 0.11448233399914898, "count": 1, "self": 0.11448233399914898 } } } } } } }