{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31244075298309326, "min": 0.30735117197036743, "max": 1.494243860244751, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9558.1875, "min": 9112.34765625, "max": 45329.3828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989975.0, "min": 29952.0, "max": 989975.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6163113713264465, "min": -0.0742742121219635, "max": 0.668003499507904, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.11398315429688, "min": -17.9743595123291, "max": 189.04498291015625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019648682326078415, "min": 0.009604482911527157, "max": 0.2914630174636841, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.678469181060791, "min": 2.7084641456604004, "max": 69.07673645019531, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07058728970100288, "min": 0.0644643053894116, "max": 0.0738104028326537, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0588093455150431, "min": 0.4965206905508658, "max": 1.0795290299643323, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018715627555046046, "min": 0.000497202369253022, "max": 0.018715627555046046, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2807344133256907, "min": 0.005966428431036264, "max": 0.2807344133256907, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.240943085146667e-05, "min": 1.240943085146667e-05, "max": 0.0004919177159021714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00018614146277200005, "min": 0.00018614146277200005, "max": 0.005421855215628999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248186666666668, "min": 0.10248186666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372280000000003, "min": 1.3886848, "max": 2.4427157999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025793848000000007, "min": 0.00025793848000000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003869077200000001, "min": 0.003869077200000001, "max": 0.1084586629, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014859267510473728, "min": 0.014859267510473728, "max": 0.46216633915901184, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2228890061378479, "min": 0.2105051875114441, "max": 3.2351644039154053, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 290.7196261682243, "min": 286.1333333333333, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31107.0, "min": 15984.0, "max": 32279.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.670020543387003, "min": -1.0000000521540642, "max": 1.6948094997377623, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.69219814240932, "min": -29.945001646876335, "max": 178.69219814240932, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.670020543387003, "min": -1.0000000521540642, "max": 1.6948094997377623, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.69219814240932, "min": -29.945001646876335, "max": 178.69219814240932, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04484530939083007, "min": 0.04484530939083007, "max": 9.45072509534657, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.798448104818817, "min": 4.471678686488303, "max": 151.21160152554512, "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": "1747652934", "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 v2 --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": "1747655355" }, "total": 2420.8599100310003, "count": 1, "self": 0.8321350750002239, "children": { "run_training.setup": { "total": 0.020975700999770197, "count": 1, "self": 0.020975700999770197 }, "TrainerController.start_learning": { "total": 2420.0067992550003, "count": 1, "self": 1.5446296361124041, "children": { "TrainerController._reset_env": { "total": 2.433267133999834, "count": 1, "self": 2.433267133999834 }, "TrainerController.advance": { "total": 2415.905521082889, "count": 64020, "self": 1.6320995739652062, "children": { "env_step": { "total": 1716.8344552880208, "count": 64020, "self": 1557.055329250772, "children": { "SubprocessEnvManager._take_step": { "total": 158.89160658711262, "count": 64020, "self": 5.053982813109542, "children": { "TorchPolicy.evaluate": { "total": 153.83762377400308, "count": 62564, "self": 153.83762377400308 } } }, "workers": { "total": 0.8875194501360966, "count": 64020, "self": 0.0, "children": { "worker_root": { "total": 2414.223065369906, "count": 64020, "is_parallel": true, "self": 978.4718187139833, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021586550001302385, "count": 1, "is_parallel": true, "self": 0.0007011620009507169, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014574929991795216, "count": 8, "is_parallel": true, "self": 0.0014574929991795216 } } }, "UnityEnvironment.step": { "total": 0.050109202999919944, "count": 1, "is_parallel": true, "self": 0.0005504600003405358, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048208999942289665, "count": 1, "is_parallel": true, "self": 0.00048208999942289665 }, "communicator.exchange": { "total": 0.047460402000069735, "count": 1, "is_parallel": true, "self": 0.047460402000069735 }, "steps_from_proto": { "total": 0.001616251000086777, "count": 1, "is_parallel": true, "self": 0.0003638439993665088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012524070007202681, "count": 8, "is_parallel": true, "self": 0.0012524070007202681 } } } } } } }, "UnityEnvironment.step": { "total": 1435.7512466559228, "count": 64019, "is_parallel": true, "self": 32.86834825801361, "children": { "UnityEnvironment._generate_step_input": { "total": 23.2808961050132, "count": 64019, "is_parallel": true, "self": 23.2808961050132 }, "communicator.exchange": { "total": 1281.274131544913, "count": 64019, "is_parallel": true, "self": 1281.274131544913 }, "steps_from_proto": { "total": 98.32787074798307, "count": 64019, "is_parallel": true, "self": 20.38281090655437, "children": { "_process_rank_one_or_two_observation": { "total": 77.9450598414287, "count": 512152, "is_parallel": true, "self": 77.9450598414287 } } } } } } } } } } }, "trainer_advance": { "total": 697.4389662209032, "count": 64020, "self": 2.943188407879461, "children": { "process_trajectory": { "total": 132.7225719260241, "count": 64020, "self": 132.47865304002426, "children": { "RLTrainer._checkpoint": { "total": 0.24391888599984668, "count": 2, "self": 0.24391888599984668 } } }, "_update_policy": { "total": 561.7732058869997, "count": 448, "self": 313.599070995072, "children": { "TorchPPOOptimizer.update": { "total": 248.17413489192768, "count": 22812, "self": 248.17413489192768 } } } } } } }, "trainer_threads": { "total": 1.1129995982628316e-06, "count": 1, "self": 1.1129995982628316e-06 }, "TrainerController._save_models": { "total": 0.12338028899921483, "count": 1, "self": 0.002047890999165247, "children": { "RLTrainer._checkpoint": { "total": 0.12133239800004958, "count": 1, "self": 0.12133239800004958 } } } } } } }