{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2095889300107956, "min": 0.2095889300107956, "max": 1.5223374366760254, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 6354.736328125, "min": 6354.736328125, "max": 46181.62890625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999873.0, "min": 29952.0, "max": 2999873.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999873.0, "min": 29952.0, "max": 2999873.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6315123438835144, "min": -0.11770230531692505, "max": 0.7383515238761902, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.82345581054688, "min": -28.366254806518555, "max": 220.0287628173828, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0033558362629264593, "min": -0.029609424993395805, "max": 0.31942421197891235, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.9396341443061829, "min": -7.698450565338135, "max": 75.70353698730469, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07024486660200799, "min": 0.06551907101501933, "max": 0.07225986183103589, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9834281324281119, "min": 0.4913150214211448, "max": 1.0838979274655383, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01571070640794646, "min": 0.00020251973996629022, "max": 0.01778578418140699, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21994988971125043, "min": 0.0022277171396291925, "max": 0.2549039862302986, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5335352031404757e-06, "min": 1.5335352031404757e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.146949284396666e-05, "min": 2.146949284396666e-05, "max": 0.0039274857908381, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051114523809523, "min": 0.10051114523809523, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071560333333333, "min": 1.3897045333333333, "max": 2.722520166666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.106340928571428e-05, "min": 6.106340928571428e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00085488773, "min": 0.00085488773, "max": 0.13092527381000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00434579374268651, "min": 0.0041083344258368015, "max": 0.38756033778190613, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.060841113328933716, "min": 0.0575166791677475, "max": 2.7129223346710205, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.8529411764706, "min": 253.25210084033614, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30585.0, "min": 15984.0, "max": 32743.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6020744888513696, "min": -1.0000000521540642, "max": 1.7156504686306981, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 163.4115978628397, "min": -32.000001668930054, "max": 199.86059799045324, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6020744888513696, "min": -1.0000000521540642, "max": 1.7156504686306981, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 163.4115978628397, "min": -32.000001668930054, "max": 199.86059799045324, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01377120000809858, "min": 0.011725296400768189, "max": 8.019388806074858, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.404662400826055, "min": 1.237680401365651, "max": 128.31022089719772, "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": "1746404716", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746412307" }, "total": 7590.533825639, "count": 1, "self": 0.4757601709998198, "children": { "run_training.setup": { "total": 0.020784198999990622, "count": 1, "self": 0.020784198999990622 }, "TrainerController.start_learning": { "total": 7590.037281269, "count": 1, "self": 5.005665708114066, "children": { "TrainerController._reset_env": { "total": 2.4791692310000144, "count": 1, "self": 2.4791692310000144 }, "TrainerController.advance": { "total": 7582.449988702885, "count": 193271, "self": 5.195924994339293, "children": { "env_step": { "total": 5451.859770614978, "count": 193271, "self": 4935.958652499008, "children": { "SubprocessEnvManager._take_step": { "total": 512.9131122348899, "count": 193271, "self": 15.43495396116191, "children": { "TorchPolicy.evaluate": { "total": 497.478158273728, "count": 187573, "self": 497.478158273728 } } }, "workers": { "total": 2.988005881079971, "count": 193271, "self": 0.0, "children": { "worker_root": { "total": 7573.441260349862, "count": 193271, "is_parallel": true, "self": 3020.2965668756806, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020338439999250113, "count": 1, "is_parallel": true, "self": 0.0006816319998961262, "children": { "_process_rank_one_or_two_observation": { "total": 0.001352212000028885, "count": 8, "is_parallel": true, "self": 0.001352212000028885 } } }, "UnityEnvironment.step": { "total": 0.0944203290000587, "count": 1, "is_parallel": true, "self": 0.0005400000002282468, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004856989999098005, "count": 1, "is_parallel": true, "self": 0.0004856989999098005 }, "communicator.exchange": { "total": 0.09165307900002517, "count": 1, "is_parallel": true, "self": 0.09165307900002517 }, "steps_from_proto": { "total": 0.0017415509998954803, "count": 1, "is_parallel": true, "self": 0.00038380099999812956, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013577499998973508, "count": 8, "is_parallel": true, "self": 0.0013577499998973508 } } } } } } }, "UnityEnvironment.step": { "total": 4553.144693474182, "count": 193270, "is_parallel": true, "self": 101.20586979283689, "children": { "UnityEnvironment._generate_step_input": { "total": 74.44578508628638, "count": 193270, "is_parallel": true, "self": 74.44578508628638 }, "communicator.exchange": { "total": 4063.6338483668615, "count": 193270, "is_parallel": true, "self": 4063.6338483668615 }, "steps_from_proto": { "total": 313.8591902281971, "count": 193270, "is_parallel": true, "self": 66.32561570274584, "children": { "_process_rank_one_or_two_observation": { "total": 247.5335745254513, "count": 1546160, "is_parallel": true, "self": 247.5335745254513 } } } } } } } } } } }, "trainer_advance": { "total": 2125.394293093568, "count": 193271, "self": 9.964480194333191, "children": { "process_trajectory": { "total": 424.22733341524645, "count": 193271, "self": 423.6321320842485, "children": { "RLTrainer._checkpoint": { "total": 0.595201330997952, "count": 6, "self": 0.595201330997952 } } }, "_update_policy": { "total": 1691.2024794839883, "count": 1388, "self": 936.5676460141913, "children": { "TorchPPOOptimizer.update": { "total": 754.6348334697971, "count": 68406, "self": 754.6348334697971 } } } } } } }, "trainer_threads": { "total": 8.620008884463459e-07, "count": 1, "self": 8.620008884463459e-07 }, "TrainerController._save_models": { "total": 0.10245676500016998, "count": 1, "self": 0.0014772569993510842, "children": { "RLTrainer._checkpoint": { "total": 0.1009795080008189, "count": 1, "self": 0.1009795080008189 } } } } } } }