{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.11817678809165955, "min": 0.11701293289661407, "max": 1.5409817695617676, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 2371.09912109375, "min": 2338.386474609375, "max": 30967.5703125, "count": 50 }, "Pyramids.Step.mean": { "value": 999874.0, "min": 19968.0, "max": 999874.0, "count": 50 }, "Pyramids.Step.sum": { "value": 999874.0, "min": 19968.0, "max": 999874.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06700120866298676, "min": -0.12325336039066315, "max": -0.007979289628565311, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -10.78719425201416, "min": -19.5972843170166, "max": -1.2846657037734985, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.7650274634361267, "min": 0.6991583108901978, "max": 1.6416171789169312, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 123.16941833496094, "min": 112.56448364257812, "max": 262.65875244140625, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0701045287638083, "min": 0.06394409583992369, "max": 0.07422602411995141, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6309407588742747, "min": 0.27546035051118345, "max": 0.7304814451330743, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0059373830372589, "min": 0.0015170208062182178, "max": 0.11480174680479972, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0534364473353301, "min": 0.013255723206650883, "max": 0.4592069872191989, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.9038656987444447e-06, "min": 2.9038656987444447e-06, "max": 0.0002969568010144, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.61347912887e-05, "min": 2.61347912887e-05, "max": 0.0025662549445817, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10096792222222223, "min": 0.10096792222222223, "max": 0.19898559999999998, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.9087113, "min": 0.7959423999999999, "max": 1.7554183, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010669543000000001, "min": 0.00010669543000000001, "max": 0.00989866144, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009602588700000001, "min": 0.0009602588700000001, "max": 0.08554628817, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.7650960087776184, "min": 0.672815203666687, "max": 2.9393796920776367, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 6.8858642578125, "min": 5.382521629333496, "max": 11.757518768310547, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 911.6666666666666, "min": 814.8095238095239, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 21880.0, "min": 15354.0, "max": 27972.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.4954833850885431, "min": -1.0000000521540642, "max": -0.14863813810405277, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -11.891601242125034, "min": -27.998401455581188, "max": -3.121400900185108, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.4954833850885431, "min": -1.0000000521540642, "max": -0.14863813810405277, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -11.891601242125034, "min": -27.998401455581188, "max": -3.121400900185108, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 6.889100055520733, "min": 6.030769028833935, "max": 41.948648661375046, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 165.3384013324976, "min": 115.35289067029953, "max": 671.1783785820007, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1788264359", "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": "1788266373" }, "total": 2013.5924258359996, "count": 1, "self": 0.4820397450002929, "children": { "run_training.setup": { "total": 0.023841647999688576, "count": 1, "self": 0.023841647999688576 }, "TrainerController.start_learning": { "total": 2013.0865444429996, "count": 1, "self": 1.2452893480331113, "children": { "TrainerController._reset_env": { "total": 2.0879786870000316, "count": 1, "self": 2.0879786870000316 }, "TrainerController.advance": { "total": 2009.6756674319663, "count": 63196, "self": 1.2515860477387832, "children": { "env_step": { "total": 1407.2298312011226, "count": 63196, "self": 1263.1738449800828, "children": { "SubprocessEnvManager._take_step": { "total": 143.3126303959457, "count": 63196, "self": 4.468975631865305, "children": { "TorchPolicy.evaluate": { "total": 138.84365476408038, "count": 62558, "self": 138.84365476408038 } } }, "workers": { "total": 0.7433558250941132, "count": 63196, "self": 0.0, "children": { "worker_root": { "total": 2007.3027805550573, "count": 63196, "is_parallel": true, "self": 854.9367617270118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018401160000394157, "count": 1, "is_parallel": true, "self": 0.0006459109999923385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011942050000470772, "count": 8, "is_parallel": true, "self": 0.0011942050000470772 } } }, "UnityEnvironment.step": { "total": 0.05081030600013037, "count": 1, "is_parallel": true, "self": 0.0005491510005413147, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004811009998775262, "count": 1, "is_parallel": true, "self": 0.0004811009998775262 }, "communicator.exchange": { "total": 0.04810058700013542, "count": 1, "is_parallel": true, "self": 0.04810058700013542 }, "steps_from_proto": { "total": 0.001679466999576107, "count": 1, "is_parallel": true, "self": 0.000332565998633072, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013469010009430349, "count": 8, "is_parallel": true, "self": 0.0013469010009430349 } } } } } } }, "UnityEnvironment.step": { "total": 1152.3660188280455, "count": 63195, "is_parallel": true, "self": 33.06918128504822, "children": { "UnityEnvironment._generate_step_input": { "total": 22.96194383315651, "count": 63195, "is_parallel": true, "self": 22.96194383315651 }, "communicator.exchange": { "total": 992.5456844318669, "count": 63195, "is_parallel": true, "self": 992.5456844318669 }, "steps_from_proto": { "total": 103.7892092779739, "count": 63195, "is_parallel": true, "self": 21.4302036247459, "children": { "_process_rank_one_or_two_observation": { "total": 82.359005653228, "count": 505560, "is_parallel": true, "self": 82.359005653228 } } } } } } } } } } }, "trainer_advance": { "total": 601.1942501831049, "count": 63196, "self": 2.352897496073183, "children": { "process_trajectory": { "total": 103.46958630704239, "count": 63196, "self": 103.22713043604244, "children": { "RLTrainer._checkpoint": { "total": 0.24245587099994736, "count": 2, "self": 0.24245587099994736 } } }, "_update_policy": { "total": 495.37176637998937, "count": 451, "self": 260.2125775389968, "children": { "TorchPPOOptimizer.update": { "total": 235.15918884099256, "count": 22818, "self": 235.15918884099256 } } } } } } }, "trainer_threads": { "total": 9.85000042419415e-07, "count": 1, "self": 9.85000042419415e-07 }, "TrainerController._save_models": { "total": 0.07760799100014992, "count": 1, "self": 0.0009221740001521539, "children": { "RLTrainer._checkpoint": { "total": 0.07668581699999777, "count": 1, "self": 0.07668581699999777 } } } } } } }