{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41059887409210205, "min": 0.4031032621860504, "max": 1.4772595167160034, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12271.9794921875, "min": 12125.345703125, "max": 44814.14453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989963.0, "min": 29952.0, "max": 989963.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.15164965391159058, "min": -0.10896016657352448, "max": 0.15164965391159058, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 38.36736297607422, "min": -26.2593994140625, "max": 38.36736297607422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006919424515217543, "min": -0.006919424515217543, "max": 0.26137885451316833, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.7506144046783447, "min": -1.7506144046783447, "max": 62.730926513671875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0687537761204563, "min": 0.06484396541452019, "max": 0.07319275093416275, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9625528656863882, "min": 0.49531079947629986, "max": 1.063081136517747, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00787608151501957, "min": 0.0003182225448021127, "max": 0.00912399763408411, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11026514121027398, "min": 0.004455115627229578, "max": 0.12773596687717753, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.565547434550001e-06, "min": 2.565547434550001e-06, "max": 9.838354447360002e-05, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.591766408370001e-05, "min": 3.591766408370001e-05, "max": 0.0010842290157711998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256545000000002, "min": 0.10256545000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359163000000001, "min": 1.3691136000000002, "max": 2.3842288000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026628845500000013, "min": 0.00026628845500000013, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037280383700000015, "min": 0.0037280383700000015, "max": 0.10844445711999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00891942624002695, "min": 0.00873647816479206, "max": 0.4181419909000397, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12487196922302246, "min": 0.12231069058179855, "max": 2.9269938468933105, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 698.0, "min": 674.2222222222222, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30014.0, "min": 15984.0, "max": 32810.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6041069467400395, "min": -1.0000000521540642, "max": 0.6145066372222371, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 25.9765987098217, "min": -32.000001668930054, "max": 27.652798675000668, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6041069467400395, "min": -1.0000000521540642, "max": 0.6145066372222371, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 25.9765987098217, "min": -32.000001668930054, "max": 27.652798675000668, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06433771157956704, "min": 0.06433771157956704, "max": 8.168297654017806, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7665215979213826, "min": 2.576814963016659, "max": 130.6927624642849, "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": "1688542495", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "1688544470" }, "total": 1975.006288345, "count": 1, "self": 0.4307719799999177, "children": { "run_training.setup": { "total": 0.04151585200008867, "count": 1, "self": 0.04151585200008867 }, "TrainerController.start_learning": { "total": 1974.5340005130001, "count": 1, "self": 1.2786678899176422, "children": { "TrainerController._reset_env": { "total": 4.125409566999906, "count": 1, "self": 4.125409566999906 }, "TrainerController.advance": { "total": 1969.0315315550824, "count": 63186, "self": 1.319476776069223, "children": { "env_step": { "total": 1330.6255264789986, "count": 63186, "self": 1222.6821296489834, "children": { "SubprocessEnvManager._take_step": { "total": 107.19564306599227, "count": 63186, "self": 4.565628669002649, "children": { "TorchPolicy.evaluate": { "total": 102.63001439698962, "count": 62560, "self": 102.63001439698962 } } }, "workers": { "total": 0.7477537640230594, "count": 63186, "self": 0.0, "children": { "worker_root": { "total": 1970.2145186460261, "count": 63186, "is_parallel": true, "self": 855.269954903044, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017130789999555418, "count": 1, "is_parallel": true, "self": 0.0005660990000251331, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011469799999304087, "count": 8, "is_parallel": true, "self": 0.0011469799999304087 } } }, "UnityEnvironment.step": { "total": 0.05049503399993682, "count": 1, "is_parallel": true, "self": 0.0005536770000844626, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047885300000416464, "count": 1, "is_parallel": true, "self": 0.00047885300000416464 }, "communicator.exchange": { "total": 0.04760029499993834, "count": 1, "is_parallel": true, "self": 0.04760029499993834 }, "steps_from_proto": { "total": 0.0018622089999098534, "count": 1, "is_parallel": true, "self": 0.00035314099989136594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015090680000184875, "count": 8, "is_parallel": true, "self": 0.0015090680000184875 } } } } } } }, "UnityEnvironment.step": { "total": 1114.9445637429822, "count": 63185, "is_parallel": true, "self": 32.80401861406426, "children": { "UnityEnvironment._generate_step_input": { "total": 22.075887652001143, "count": 63185, "is_parallel": true, "self": 22.075887652001143 }, "communicator.exchange": { "total": 961.0932881209783, "count": 63185, "is_parallel": true, "self": 961.0932881209783 }, "steps_from_proto": { "total": 98.97136935593858, "count": 63185, "is_parallel": true, "self": 18.91882208701702, "children": { "_process_rank_one_or_two_observation": { "total": 80.05254726892156, "count": 505480, "is_parallel": true, "self": 80.05254726892156 } } } } } } } } } } }, "trainer_advance": { "total": 637.0865283000145, "count": 63186, "self": 2.335330970977566, "children": { "process_trajectory": { "total": 106.39444919504047, "count": 63186, "self": 106.19011161304059, "children": { "RLTrainer._checkpoint": { "total": 0.20433758199988006, "count": 2, "self": 0.20433758199988006 } } }, "_update_policy": { "total": 528.3567481339965, "count": 437, "self": 336.5212414470078, "children": { "TorchPPOOptimizer.update": { "total": 191.83550668698865, "count": 22848, "self": 191.83550668698865 } } } } } } }, "trainer_threads": { "total": 1.1189999895577785e-06, "count": 1, "self": 1.1189999895577785e-06 }, "TrainerController._save_models": { "total": 0.09839038200016148, "count": 1, "self": 0.0017902539998431166, "children": { "RLTrainer._checkpoint": { "total": 0.09660012800031836, "count": 1, "self": 0.09660012800031836 } } } } } } }