| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.1410285234451294, | |
| "min": 0.13927701115608215, | |
| "max": 1.545820713043213, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 4219.5732421875, | |
| "min": 4173.853515625, | |
| "max": 46894.015625, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2999890.0, | |
| "min": 29952.0, | |
| "max": 2999890.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2999890.0, | |
| "min": 29952.0, | |
| "max": 2999890.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.7698922753334045, | |
| "min": -0.1635073870420456, | |
| "max": 0.8786913156509399, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 227.8881072998047, | |
| "min": -38.751251220703125, | |
| "max": 268.0008544921875, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.010623428970575333, | |
| "min": -0.008979268372058868, | |
| "max": 0.14587080478668213, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 3.1445350646972656, | |
| "min": -2.6039879322052, | |
| "max": 35.15486526489258, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06883674581602499, | |
| "min": 0.06395330794559301, | |
| "max": 0.07315455795744331, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9637144414243498, | |
| "min": 0.4962081570143479, | |
| "max": 1.0973183693616497, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.0149401764954272, | |
| "min": 0.00042585140106703563, | |
| "max": 0.016667019907063582, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.2091624709359808, | |
| "min": 0.005110216812804428, | |
| "max": 0.23708829763927497, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 1.4502923737452385e-06, | |
| "min": 1.4502923737452385e-06, | |
| "max": 0.00029838354339596195, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 2.030409323243334e-05, | |
| "min": 2.030409323243334e-05, | |
| "max": 0.004010933363022233, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10048339761904765, | |
| "min": 0.10048339761904765, | |
| "max": 0.19946118095238097, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.406767566666667, | |
| "min": 1.3962282666666668, | |
| "max": 2.8125845999999997, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 5.829142214285716e-05, | |
| "min": 5.829142214285716e-05, | |
| "max": 0.009946171977142856, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0008160799100000002, | |
| "min": 0.0008160799100000002, | |
| "max": 0.13370407889000002, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.0063204094767570496, | |
| "min": 0.0063204094767570496, | |
| "max": 0.24973034858703613, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.0884857326745987, | |
| "min": 0.0884857326745987, | |
| "max": 1.748112440109253, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 219.9927536231884, | |
| "min": 212.231884057971, | |
| "max": 999.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 30359.0, | |
| "min": 15984.0, | |
| "max": 33751.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.7220159252916558, | |
| "min": -1.0000000521540642, | |
| "max": 1.782765139007207, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 237.6381976902485, | |
| "min": -30.998201623558998, | |
| "max": 246.83879802376032, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.7220159252916558, | |
| "min": -1.0000000521540642, | |
| "max": 1.782765139007207, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 237.6381976902485, | |
| "min": -30.998201623558998, | |
| "max": 246.83879802376032, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.01459184837699138, | |
| "min": 0.014560451048082818, | |
| "max": 4.968541800044477, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.0136750760248106, | |
| "min": 1.9219795383469318, | |
| "max": 79.49666880071163, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1741752160", | |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsRND1 --no-graphics", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.6.0+cu124", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1741759897" | |
| }, | |
| "total": 7736.25186338, | |
| "count": 1, | |
| "self": 0.4986571159997766, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.022445892999996886, | |
| "count": 1, | |
| "self": 0.022445892999996886 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 7735.7307603710005, | |
| "count": 1, | |
| "self": 4.499475757346772, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.081650804999981, | |
| "count": 1, | |
| "self": 3.081650804999981 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 7728.060415609653, | |
| "count": 195372, | |
| "self": 4.548937730580292, | |
| "children": { | |
| "env_step": { | |
| "total": 5608.809174490949, | |
| "count": 195372, | |
| "self": 5121.494388198853, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 484.7177464410853, | |
| "count": 195372, | |
| "self": 14.688961682108811, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 470.0287847589765, | |
| "count": 187546, | |
| "self": 470.0287847589765 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.597039851010834, | |
| "count": 195372, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 7719.330573928743, | |
| "count": 195372, | |
| "is_parallel": true, | |
| "self": 2965.3186938117087, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.005148101999964183, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0036899180000773413, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0014581839998868418, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0014581839998868418 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05094889500003319, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005515530000366198, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005010879999645113, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005010879999645113 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04811954199999491, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04811954199999491 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0017767120000371506, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00050198400009549, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012747279999416605, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012747279999416605 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 4754.011880117035, | |
| "count": 195371, | |
| "is_parallel": true, | |
| "self": 100.96555125312261, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 72.68012815198585, | |
| "count": 195371, | |
| "is_parallel": true, | |
| "self": 72.68012815198585 | |
| }, | |
| "communicator.exchange": { | |
| "total": 4271.699032606831, | |
| "count": 195371, | |
| "is_parallel": true, | |
| "self": 4271.699032606831 | |
| }, | |
| "steps_from_proto": { | |
| "total": 308.6671681050959, | |
| "count": 195371, | |
| "is_parallel": true, | |
| "self": 64.21089549877837, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 244.45627260631755, | |
| "count": 1562968, | |
| "is_parallel": true, | |
| "self": 244.45627260631755 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 2114.702303388124, | |
| "count": 195372, | |
| "self": 9.21835063817116, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 418.08921351393826, | |
| "count": 195372, | |
| "self": 417.43671333093755, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.6525001830007113, | |
| "count": 6, | |
| "self": 0.6525001830007113 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1687.3947392360146, | |
| "count": 1401, | |
| "self": 921.4696583470713, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 765.9250808889433, | |
| "count": 68367, | |
| "self": 765.9250808889433 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.810002327663824e-07, | |
| "count": 1, | |
| "self": 8.810002327663824e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.08921731800000998, | |
| "count": 1, | |
| "self": 0.0016219300005104742, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.08759538799949951, | |
| "count": 1, | |
| "self": 0.08759538799949951 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |