{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30965563654899597, "min": 0.30437004566192627, "max": 1.4625712633132935, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9413.53125, "min": 8976.1455078125, "max": 44368.5625, "count": 33 }, "Pyramids.Step.mean": { "value": 989894.0, "min": 29995.0, "max": 989894.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989894.0, "min": 29995.0, "max": 989894.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.529508113861084, "min": -0.08502715080976486, "max": 0.5423809289932251, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.5557098388672, "min": -20.236461639404297, "max": 151.32427978515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007025334518402815, "min": -0.042041316628456116, "max": 0.4310765266418457, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9179162979125977, "min": -10.930742263793945, "max": 110.78666687011719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0680888175055941, "min": 0.06588538287213028, "max": 0.07471546027956347, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9532434450783174, "min": 0.5977236822365077, "max": 1.0556617068941705, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014555690290474987, "min": 0.0008786138701830197, "max": 0.02586244462694998, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20377966406664982, "min": 0.011421980312379256, "max": 0.3879366694042497, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.72835456677143e-06, "min": 7.72835456677143e-06, "max": 0.0002952171390942875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010819696393480001, "min": 0.00010819696393480001, "max": 0.0037579873473375996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257608571428571, "min": 0.10257608571428571, "max": 0.19840571250000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360652, "min": 1.4360652, "max": 2.6526624000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002673509628571429, "min": 0.0002673509628571429, "max": 0.00984073067875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037429134800000007, "min": 0.0037429134800000007, "max": 0.12528097376, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010857143439352512, "min": 0.010857143439352512, "max": 0.4915505051612854, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15200001001358032, "min": 0.15200001001358032, "max": 3.932404041290283, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 373.8125, "min": 336.1931818181818, "max": 998.4230769230769, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29905.0, "min": 16794.0, "max": 34134.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5011624746024608, "min": -0.9304667180686286, "max": 1.6410727050494065, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.09299796819687, "min": -30.705401696264744, "max": 144.41439804434776, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5011624746024608, "min": -0.9304667180686286, "max": 1.6410727050494065, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.09299796819687, "min": -30.705401696264744, "max": 144.41439804434776, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0416686785814818, "min": 0.03786970848027109, "max": 10.948443429435, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.333494286518544, "min": 3.3325343462638557, "max": 186.123538300395, "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": "1692769339", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1692771684" }, "total": 2344.032611235, "count": 1, "self": 0.5454444799993325, "children": { "run_training.setup": { "total": 0.04083253400017384, "count": 1, "self": 0.04083253400017384 }, "TrainerController.start_learning": { "total": 2343.446334221, "count": 1, "self": 1.5915348500589062, "children": { "TrainerController._reset_env": { "total": 4.161878548000004, "count": 1, "self": 4.161878548000004 }, "TrainerController.advance": { "total": 2337.5953172739414, "count": 63919, "self": 1.5476113328854808, "children": { "env_step": { "total": 1644.4520979660545, "count": 63919, "self": 1526.3325737141035, "children": { "SubprocessEnvManager._take_step": { "total": 117.17676539799413, "count": 63919, "self": 5.210261126007026, "children": { "TorchPolicy.evaluate": { "total": 111.9665042719871, "count": 62551, "self": 111.9665042719871 } } }, "workers": { "total": 0.9427588539567751, "count": 63919, "self": 0.0, "children": { "worker_root": { "total": 2337.704104787915, "count": 63919, "is_parallel": true, "self": 936.5835461769507, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019750660001136566, "count": 1, "is_parallel": true, "self": 0.0005654430001413857, "children": { "_process_rank_one_or_two_observation": { "total": 0.001409622999972271, "count": 8, "is_parallel": true, "self": 0.001409622999972271 } } }, "UnityEnvironment.step": { "total": 0.048849787000108336, "count": 1, "is_parallel": true, "self": 0.0005827680001857516, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005298749999838037, "count": 1, "is_parallel": true, "self": 0.0005298749999838037 }, "communicator.exchange": { "total": 0.04567675099997359, "count": 1, "is_parallel": true, "self": 0.04567675099997359 }, "steps_from_proto": { "total": 0.002060392999965188, "count": 1, "is_parallel": true, "self": 0.00037684799985981954, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016835450001053687, "count": 8, "is_parallel": true, "self": 0.0016835450001053687 } } } } } } }, "UnityEnvironment.step": { "total": 1401.1205586109645, "count": 63918, "is_parallel": true, "self": 36.03965733684208, "children": { "UnityEnvironment._generate_step_input": { "total": 24.379487401021834, "count": 63918, "is_parallel": true, "self": 24.379487401021834 }, "communicator.exchange": { "total": 1229.1609794310828, "count": 63918, "is_parallel": true, "self": 1229.1609794310828 }, "steps_from_proto": { "total": 111.54043444201784, "count": 63918, "is_parallel": true, "self": 22.11733000099366, "children": { "_process_rank_one_or_two_observation": { "total": 89.42310444102418, "count": 511344, "is_parallel": true, "self": 89.42310444102418 } } } } } } } } } } }, "trainer_advance": { "total": 691.5956079750013, "count": 63919, "self": 3.032254092023777, "children": { "process_trajectory": { "total": 118.87114380497587, "count": 63919, "self": 118.65246198897603, "children": { "RLTrainer._checkpoint": { "total": 0.21868181599984382, "count": 2, "self": 0.21868181599984382 } } }, "_update_policy": { "total": 569.6922100780016, "count": 459, "self": 371.5105803019758, "children": { "TorchPPOOptimizer.update": { "total": 198.18162977602583, "count": 22773, "self": 198.18162977602583 } } } } } } }, "trainer_threads": { "total": 9.739997040014714e-07, "count": 1, "self": 9.739997040014714e-07 }, "TrainerController._save_models": { "total": 0.09760257500010994, "count": 1, "self": 0.0014999909999460215, "children": { "RLTrainer._checkpoint": { "total": 0.09610258400016392, "count": 1, "self": 0.09610258400016392 } } } } } } }