{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2340954691171646, "min": 0.2340954691171646, "max": 1.4750369787216187, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6996.6455078125, "min": 6996.6455078125, "max": 44746.72265625, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29877.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29877.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6796271204948425, "min": -0.09170316159725189, "max": 0.7362886071205139, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 198.45111083984375, "min": -22.19216537475586, "max": 212.70626831054688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0033130382653325796, "min": -0.012158521451056004, "max": 0.23359240591526031, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9674071669578552, "min": -3.4894957542419434, "max": 56.29576873779297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07291047271259235, "min": 0.06489813529298685, "max": 0.07291047271259235, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.020746617976293, "min": 0.5691190106414764, "max": 1.077183034554051, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016552837650855436, "min": 0.000758918101813668, "max": 0.016733458914954792, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2317397271119761, "min": 0.00758918101813668, "max": 0.24692492073518224, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.310411848942857e-06, "min": 7.310411848942857e-06, "max": 0.0002948484392171875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001023457658852, "min": 0.0001023457658852, "max": 0.0036331423889526, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243677142857144, "min": 0.10243677142857144, "max": 0.19828281250000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341148000000001, "min": 1.4341148000000001, "max": 2.7075837000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002534334657142857, "min": 0.0002534334657142857, "max": 0.009828452968749998, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035480685200000002, "min": 0.0035480685200000002, "max": 0.12112363525999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010613097809255123, "min": 0.010613097809255123, "max": 0.2774602770805359, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14858336746692657, "min": 0.14858336746692657, "max": 2.219682216644287, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 263.83898305084745, "min": 256.26446280991735, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31133.0, "min": 16420.0, "max": 32689.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7368717812574828, "min": -0.9999750521965325, "max": 1.7368717812574828, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 203.21399840712547, "min": -31.99920167028904, "max": 206.99039801210165, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7368717812574828, "min": -0.9999750521965325, "max": 1.7368717812574828, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 203.21399840712547, "min": -31.99920167028904, "max": 206.99039801210165, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028847393650550626, "min": 0.02838719922862151, "max": 5.159864254734096, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3751450571144233, "min": 3.243101114203455, "max": 87.71769233047962, "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": "1787554072", "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=Pyramids Training --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1787556718" }, "total": 2645.9598824400005, "count": 1, "self": 0.47861995400035084, "children": { "run_training.setup": { "total": 0.024441653999929258, "count": 1, "self": 0.024441653999929258 }, "TrainerController.start_learning": { "total": 2645.456820832, "count": 1, "self": 1.5346419720185622, "children": { "TrainerController._reset_env": { "total": 2.184334257000046, "count": 1, "self": 2.184334257000046 }, "TrainerController.advance": { "total": 2641.6604345059814, "count": 64668, "self": 1.5022229999967749, "children": { "env_step": { "total": 1997.0341455880334, "count": 64668, "self": 1836.5413906329209, "children": { "SubprocessEnvManager._take_step": { "total": 159.59578145608748, "count": 64668, "self": 4.873243983158773, "children": { "TorchPolicy.evaluate": { "total": 154.7225374729287, "count": 62570, "self": 154.7225374729287 } } }, "workers": { "total": 0.89697349902508, "count": 64668, "self": 0.0, "children": { "worker_root": { "total": 2639.1846569410386, "count": 64668, "is_parallel": true, "self": 927.90406798408, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018189649999840185, "count": 1, "is_parallel": true, "self": 0.0005693379994227143, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012496270005613042, "count": 8, "is_parallel": true, "self": 0.0012496270005613042 } } }, "UnityEnvironment.step": { "total": 0.050861680999787495, "count": 1, "is_parallel": true, "self": 0.0005213340000409517, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005057509997641318, "count": 1, "is_parallel": true, "self": 0.0005057509997641318 }, "communicator.exchange": { "total": 0.04821676099982142, "count": 1, "is_parallel": true, "self": 0.04821676099982142 }, "steps_from_proto": { "total": 0.0016178350001609942, "count": 1, "is_parallel": true, "self": 0.00034889799917436903, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012689370009866252, "count": 8, "is_parallel": true, "self": 0.0012689370009866252 } } } } } } }, "UnityEnvironment.step": { "total": 1711.2805889569586, "count": 64667, "is_parallel": true, "self": 35.31568874388995, "children": { "UnityEnvironment._generate_step_input": { "total": 24.344442909944064, "count": 64667, "is_parallel": true, "self": 24.344442909944064 }, "communicator.exchange": { "total": 1538.1290136730981, "count": 64667, "is_parallel": true, "self": 1538.1290136730981 }, "steps_from_proto": { "total": 113.49144363002642, "count": 64667, "is_parallel": true, "self": 23.63451492220065, "children": { "_process_rank_one_or_two_observation": { "total": 89.85692870782577, "count": 517336, "is_parallel": true, "self": 89.85692870782577 } } } } } } } } } } }, "trainer_advance": { "total": 643.1240659179512, "count": 64668, "self": 2.8687183379729504, "children": { "process_trajectory": { "total": 117.38573008897856, "count": 64668, "self": 117.15103544497833, "children": { "RLTrainer._checkpoint": { "total": 0.23469464400022844, "count": 2, "self": 0.23469464400022844 } } }, "_update_policy": { "total": 522.8696174909996, "count": 458, "self": 279.07841316298527, "children": { "TorchPPOOptimizer.update": { "total": 243.79120432801437, "count": 22800, "self": 243.79120432801437 } } } } } } }, "trainer_threads": { "total": 1.0170006135012954e-06, "count": 1, "self": 1.0170006135012954e-06 }, "TrainerController._save_models": { "total": 0.07740907999959745, "count": 1, "self": 0.001172415999462828, "children": { "RLTrainer._checkpoint": { "total": 0.07623666400013462, "count": 1, "self": 0.07623666400013462 } } } } } } }