{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5278274416923523, "min": 0.5238612294197083, "max": 1.4264739751815796, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15902.384765625, "min": 15615.255859375, "max": 43273.515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29971.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29971.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.17432379722595215, "min": -0.10377410799264908, "max": 0.24251849949359894, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 43.929595947265625, "min": -25.11333465576172, "max": 61.84221649169922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008939574472606182, "min": 0.0035323123447597027, "max": 0.3342987895011902, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.252772808074951, "min": 0.8901427388191223, "max": 79.5631103515625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06650228196506731, "min": 0.0639622387052489, "max": 0.07317192745006265, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9310319475109423, "min": 0.4997715534616915, "max": 1.060928463198555, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008351795632278116, "min": 0.0001401915527483047, "max": 0.009569305434120502, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11692513885189362, "min": 0.0016822986329796561, "max": 0.14353958151180754, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.456490371678568e-06, "min": 7.456490371678568e-06, "max": 0.0002952375873017571, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010439086520349994, "min": 0.00010439086520349994, "max": 0.0033319509893496996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248546428571428, "min": 0.10248546428571428, "max": 0.19841252857142858, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347965, "min": 1.3888877, "max": 2.3843311000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002582978821428571, "min": 0.0002582978821428571, "max": 0.009841411604285713, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036161703499999987, "min": 0.0036161703499999987, "max": 0.11107396496999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009348786436021328, "min": 0.009348786436021328, "max": 0.32108768820762634, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13088300824165344, "min": 0.13088300824165344, "max": 2.2476139068603516, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 658.5681818181819, "min": 592.7872340425532, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28977.0, "min": 16514.0, "max": 32760.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9037821799516678, "min": -0.9999500522390008, "max": 0.9037821799516678, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.67019809782505, "min": -31.998401671648026, "max": 43.130998477339745, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9037821799516678, "min": -0.9999500522390008, "max": 0.9037821799516678, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.67019809782505, "min": -31.998401671648026, "max": 43.130998477339745, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06456249599448509, "min": 0.06272698748459031, "max": 5.578721653450938, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.905312319751829, "min": 2.905312319751829, "max": 94.83826810866594, "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": "1679734960", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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 --force", "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": "1679737110" }, "total": 2149.198328728, "count": 1, "self": 0.4883026340003198, "children": { "run_training.setup": { "total": 0.12473185199996806, "count": 1, "self": 0.12473185199996806 }, "TrainerController.start_learning": { "total": 2148.5852942419997, "count": 1, "self": 1.3935922030445909, "children": { "TrainerController._reset_env": { "total": 6.2242930110001, "count": 1, "self": 6.2242930110001 }, "TrainerController.advance": { "total": 2140.8617318949555, "count": 63251, "self": 1.5911163169866995, "children": { "env_step": { "total": 1487.0000204480389, "count": 63251, "self": 1370.4269662111162, "children": { "SubprocessEnvManager._take_step": { "total": 115.7377016689502, "count": 63251, "self": 5.050899038018997, "children": { "TorchPolicy.evaluate": { "total": 110.6868026309312, "count": 62576, "self": 110.6868026309312 } } }, "workers": { "total": 0.8353525679724498, "count": 63251, "self": 0.0, "children": { "worker_root": { "total": 2143.7346812729543, "count": 63251, "is_parallel": true, "self": 896.0741023779253, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017889869998271024, "count": 1, "is_parallel": true, "self": 0.000564875999771175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012241110000559274, "count": 8, "is_parallel": true, "self": 0.0012241110000559274 } } }, "UnityEnvironment.step": { "total": 0.08811649800009036, "count": 1, "is_parallel": true, "self": 0.0005902279999645543, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005694449998827622, "count": 1, "is_parallel": true, "self": 0.0005694449998827622 }, "communicator.exchange": { "total": 0.08492650200014396, "count": 1, "is_parallel": true, "self": 0.08492650200014396 }, "steps_from_proto": { "total": 0.002030323000099088, "count": 1, "is_parallel": true, "self": 0.0006321659998320683, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013981570002670196, "count": 8, "is_parallel": true, "self": 0.0013981570002670196 } } } } } } }, "UnityEnvironment.step": { "total": 1247.660578895029, "count": 63250, "is_parallel": true, "self": 32.29595724399792, "children": { "UnityEnvironment._generate_step_input": { "total": 24.70859236403021, "count": 63250, "is_parallel": true, "self": 24.70859236403021 }, "communicator.exchange": { "total": 1091.7564600410276, "count": 63250, "is_parallel": true, "self": 1091.7564600410276 }, "steps_from_proto": { "total": 98.89956924597323, "count": 63250, "is_parallel": true, "self": 21.2277243213764, "children": { "_process_rank_one_or_two_observation": { "total": 77.67184492459683, "count": 506000, "is_parallel": true, "self": 77.67184492459683 } } } } } } } } } } }, "trainer_advance": { "total": 652.2705951299301, "count": 63251, "self": 2.486525832970983, "children": { "process_trajectory": { "total": 123.0351350519561, "count": 63251, "self": 122.81202976495638, "children": { "RLTrainer._checkpoint": { "total": 0.22310528699972565, "count": 2, "self": 0.22310528699972565 } } }, "_update_policy": { "total": 526.748934245003, "count": 442, "self": 338.47214949102977, "children": { "TorchPPOOptimizer.update": { "total": 188.2767847539733, "count": 22824, "self": 188.2767847539733 } } } } } } }, "trainer_threads": { "total": 8.059996616793796e-07, "count": 1, "self": 8.059996616793796e-07 }, "TrainerController._save_models": { "total": 0.10567632699985552, "count": 1, "self": 0.0014394149998224748, "children": { "RLTrainer._checkpoint": { "total": 0.10423691200003304, "count": 1, "self": 0.10423691200003304 } } } } } } }