{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5660085678100586, "min": 0.5660085678100586, "max": 1.4883811473846436, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16944.033203125, "min": 16944.033203125, "max": 45151.53125, "count": 33 }, "Pyramids.Step.mean": { "value": 989900.0, "min": 29956.0, "max": 989900.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989900.0, "min": 29956.0, "max": 989900.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09211874008178711, "min": -0.10427673161029816, "max": 0.11050771921873093, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 22.93756675720215, "min": -25.130691528320312, "max": 27.737438201904297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010952141135931015, "min": 0.006063994951546192, "max": 0.3841569423675537, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.727083206176758, "min": 1.4796147346496582, "max": 91.42935180664062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06937955640643152, "min": 0.06459989592221668, "max": 0.07375391059133242, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9713137896900412, "min": 0.49988903680009417, "max": 1.0127880233190958, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007916999754248864, "min": 0.00020091309225084926, "max": 0.008516817445106987, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11083799655948409, "min": 0.0022100440147593417, "max": 0.11923544423149782, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.674590298978568e-06, "min": 7.674590298978568e-06, "max": 0.0002952382301586857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010744426418569996, "min": 0.00010744426418569996, "max": 0.0032559722146759994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255816428571429, "min": 0.10255816428571429, "max": 0.19841274285714286, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358143, "min": 1.3888892, "max": 2.4011498000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026556061214285705, "min": 0.00026556061214285705, "max": 0.009841433011428572, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037178485699999987, "min": 0.0037178485699999987, "max": 0.10855386759999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010179379023611546, "min": 0.010179379023611546, "max": 0.3907947540283203, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1425113081932068, "min": 0.1425113081932068, "max": 2.735563278198242, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 714.4047619047619, "min": 714.4047619047619, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30005.0, "min": 16627.0, "max": 32105.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.4281904321341288, "min": -0.999987552408129, "max": 0.4281904321341288, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 17.983998149633408, "min": -31.999601677060127, "max": 17.983998149633408, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.4281904321341288, "min": -0.999987552408129, "max": 0.4281904321341288, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 17.983998149633408, "min": -31.999601677060127, "max": 17.983998149633408, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07516576584575455, "min": 0.07516576584575455, "max": 7.226886574288502, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1569621655216906, "min": 3.1569621655216906, "max": 122.85707176290452, "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": "1691755777", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691758099" }, "total": 2321.8669973570004, "count": 1, "self": 0.5344020230008937, "children": { "run_training.setup": { "total": 0.039832857999954285, "count": 1, "self": 0.039832857999954285 }, "TrainerController.start_learning": { "total": 2321.2927624759996, "count": 1, "self": 1.960449499022161, "children": { "TrainerController._reset_env": { "total": 5.43699649500013, "count": 1, "self": 5.43699649500013 }, "TrainerController.advance": { "total": 2313.768929745978, "count": 63254, "self": 1.9312989770637614, "children": { "env_step": { "total": 1591.997571755986, "count": 63254, "self": 1453.4913048239446, "children": { "SubprocessEnvManager._take_step": { "total": 137.39014602201314, "count": 63254, "self": 5.673114109013568, "children": { "TorchPolicy.evaluate": { "total": 131.71703191299957, "count": 62571, "self": 131.71703191299957 } } }, "workers": { "total": 1.1161209100282576, "count": 63254, "self": 0.0, "children": { "worker_root": { "total": 2315.3117363060965, "count": 63254, "is_parallel": true, "self": 1001.6938247431622, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028826419998040365, "count": 1, "is_parallel": true, "self": 0.0008495489996676042, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020330930001364322, "count": 8, "is_parallel": true, "self": 0.0020330930001364322 } } }, "UnityEnvironment.step": { "total": 0.04837155299992446, "count": 1, "is_parallel": true, "self": 0.0005701769996449002, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005303920002006635, "count": 1, "is_parallel": true, "self": 0.0005303920002006635 }, "communicator.exchange": { "total": 0.04538303100025587, "count": 1, "is_parallel": true, "self": 0.04538303100025587 }, "steps_from_proto": { "total": 0.0018879529998230282, "count": 1, "is_parallel": true, "self": 0.00041612099994381424, "children": { "_process_rank_one_or_two_observation": { "total": 0.001471831999879214, "count": 8, "is_parallel": true, "self": 0.001471831999879214 } } } } } } }, "UnityEnvironment.step": { "total": 1313.6179115629343, "count": 63253, "is_parallel": true, "self": 37.89748967391188, "children": { "UnityEnvironment._generate_step_input": { "total": 27.163449657067304, "count": 63253, "is_parallel": true, "self": 27.163449657067304 }, "communicator.exchange": { "total": 1125.3928022490268, "count": 63253, "is_parallel": true, "self": 1125.3928022490268 }, "steps_from_proto": { "total": 123.16416998292834, "count": 63253, "is_parallel": true, "self": 25.018678697726045, "children": { "_process_rank_one_or_two_observation": { "total": 98.1454912852023, "count": 506024, "is_parallel": true, "self": 98.1454912852023 } } } } } } } } } } }, "trainer_advance": { "total": 719.8400590129281, "count": 63254, "self": 3.230449915963618, "children": { "process_trajectory": { "total": 126.69108286096434, "count": 63254, "self": 126.45520765996343, "children": { "RLTrainer._checkpoint": { "total": 0.23587520100090842, "count": 2, "self": 0.23587520100090842 } } }, "_update_policy": { "total": 589.9185262360002, "count": 444, "self": 382.659954494035, "children": { "TorchPPOOptimizer.update": { "total": 207.25857174196517, "count": 22773, "self": 207.25857174196517 } } } } } } }, "trainer_threads": { "total": 1.2599994079209864e-06, "count": 1, "self": 1.2599994079209864e-06 }, "TrainerController._save_models": { "total": 0.12638547599999583, "count": 1, "self": 0.0015421929992953665, "children": { "RLTrainer._checkpoint": { "total": 0.12484328300070047, "count": 1, "self": 0.12484328300070047 } } } } } } }