{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4000454843044281, "min": 0.393078476190567, "max": 1.4669886827468872, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12065.3720703125, "min": 11767.197265625, "max": 44502.5703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.518269956111908, "min": -0.10164462774991989, "max": 0.6121885776519775, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.96942138671875, "min": -24.394710540771484, "max": 168.37420654296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004149746615439653, "min": -0.06279049813747406, "max": 0.3129226863384247, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.12873113155365, "min": -16.82785415649414, "max": 75.41436767578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06833367078775066, "min": 0.06468995308150675, "max": 0.07500020510772067, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0250050618162598, "min": 0.4872830498307253, "max": 1.0500028715080894, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014384797636953677, "min": 0.00023484497477365286, "max": 0.01708835576538972, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21577196455430514, "min": 0.0030529846720574873, "max": 0.2392369807154561, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4193375269200025e-06, "min": 7.4193375269200025e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011129006290380003, "min": 0.00011129006290380003, "max": 0.0035080211306596993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247308, "min": 0.10247308, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5370962, "min": 1.3886848, "max": 2.5693403000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002570606920000001, "min": 0.0002570606920000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038559103800000012, "min": 0.0038559103800000012, "max": 0.11695709597000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011262333020567894, "min": 0.011262333020567894, "max": 0.49199262261390686, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16893500089645386, "min": 0.16059304773807526, "max": 3.443948268890381, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.0120481927711, "min": 294.6354166666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28968.0, "min": 15984.0, "max": 32937.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5744867327522083, "min": -1.0000000521540642, "max": 1.6594474038358815, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.68239881843328, "min": -31.999601677060127, "max": 160.96639817208052, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5744867327522083, "min": -1.0000000521540642, "max": 1.6594474038358815, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.68239881843328, "min": -31.999601677060127, "max": 160.96639817208052, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04112723002880699, "min": 0.036506625144387184, "max": 9.41786449123174, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4135600923909806, "min": 3.4135600923909806, "max": 150.68583185970783, "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": "1750937404", "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=PyramidsTraining --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750939612" }, "total": 2208.894992316, "count": 1, "self": 0.4505764499999714, "children": { "run_training.setup": { "total": 0.02450941500001136, "count": 1, "self": 0.02450941500001136 }, "TrainerController.start_learning": { "total": 2208.419906451, "count": 1, "self": 1.3299786979673627, "children": { "TrainerController._reset_env": { "total": 3.4779777699999954, "count": 1, "self": 3.4779777699999954 }, "TrainerController.advance": { "total": 2203.522351243032, "count": 63864, "self": 1.4606416469578107, "children": { "env_step": { "total": 1556.4298790440355, "count": 63864, "self": 1413.9875688660786, "children": { "SubprocessEnvManager._take_step": { "total": 141.65973554799092, "count": 63864, "self": 4.385947760977842, "children": { "TorchPolicy.evaluate": { "total": 137.27378778701308, "count": 62560, "self": 137.27378778701308 } } }, "workers": { "total": 0.7825746299658931, "count": 63864, "self": 0.0, "children": { "worker_root": { "total": 2201.8371072889977, "count": 63864, "is_parallel": true, "self": 899.3172627850104, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052916159999654155, "count": 1, "is_parallel": true, "self": 0.003961028999924565, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013305870000408504, "count": 8, "is_parallel": true, "self": 0.0013305870000408504 } } }, "UnityEnvironment.step": { "total": 0.04718179100001407, "count": 1, "is_parallel": true, "self": 0.0005544409999629352, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046124100003908097, "count": 1, "is_parallel": true, "self": 0.00046124100003908097 }, "communicator.exchange": { "total": 0.04463517599998568, "count": 1, "is_parallel": true, "self": 0.04463517599998568 }, "steps_from_proto": { "total": 0.0015309330000263799, "count": 1, "is_parallel": true, "self": 0.00031870200007233507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012122309999540448, "count": 8, "is_parallel": true, "self": 0.0012122309999540448 } } } } } } }, "UnityEnvironment.step": { "total": 1302.5198445039873, "count": 63863, "is_parallel": true, "self": 31.97726853596305, "children": { "UnityEnvironment._generate_step_input": { "total": 21.843491688012932, "count": 63863, "is_parallel": true, "self": 21.843491688012932 }, "communicator.exchange": { "total": 1156.0529366630028, "count": 63863, "is_parallel": true, "self": 1156.0529366630028 }, "steps_from_proto": { "total": 92.64614761700852, "count": 63863, "is_parallel": true, "self": 18.43739413713479, "children": { "_process_rank_one_or_two_observation": { "total": 74.20875347987374, "count": 510904, "is_parallel": true, "self": 74.20875347987374 } } } } } } } } } } }, "trainer_advance": { "total": 645.631830552039, "count": 63864, "self": 2.565234046005685, "children": { "process_trajectory": { "total": 123.21916525903237, "count": 63864, "self": 122.98435487903237, "children": { "RLTrainer._checkpoint": { "total": 0.23481037999999899, "count": 2, "self": 0.23481037999999899 } } }, "_update_policy": { "total": 519.8474312470009, "count": 451, "self": 291.3695140189731, "children": { "TorchPPOOptimizer.update": { "total": 228.47791722802782, "count": 22803, "self": 228.47791722802782 } } } } } } }, "trainer_threads": { "total": 9.1600031737471e-07, "count": 1, "self": 9.1600031737471e-07 }, "TrainerController._save_models": { "total": 0.08959782400006588, "count": 1, "self": 0.0012195270001029712, "children": { "RLTrainer._checkpoint": { "total": 0.08837829699996291, "count": 1, "self": 0.08837829699996291 } } } } } } }