{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41065919399261475, "min": 0.41065919399261475, "max": 1.1121141910552979, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12247.5, "min": 11388.048828125, "max": 29578.67578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.531220018863678, "min": -0.1878412365913391, "max": 0.5939654111862183, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.08551025390625, "min": -31.328060150146484, "max": 167.4982452392578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.033500947058200836, "min": 0.022572945803403854, "max": 0.6026591062545776, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.212759971618652, "min": 6.2752790451049805, "max": 107.45845031738281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06803343177030219, "min": 0.06569015766061577, "max": 0.07776449003722519, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9524680447842306, "min": 0.15552898007445037, "max": 1.0717936285266965, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01388946787413997, "min": 0.00018715329913944907, "max": 0.016395463587416868, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19445255023795957, "min": 0.0024329928888128377, "max": 0.23718496624981827, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.306768993014289e-06, "min": 7.306768993014289e-06, "max": 0.000292128002624, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010229476590220005, "min": 0.00010229476590220005, "max": 0.0036336997887668, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243555714285714, "min": 0.10243555714285714, "max": 0.19737600000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340978, "min": 0.39475200000000005, "max": 2.6112332000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002533121585714288, "min": 0.0002533121585714288, "max": 0.009737862400000002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035463702200000027, "min": 0.0035463702200000027, "max": 0.12114219668000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03340219333767891, "min": 0.032988473773002625, "max": 0.2825556993484497, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.46763068437576294, "min": 0.46727994084358215, "max": 2.0632035732269287, "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 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 374.8974358974359, "min": 321.24242424242425, "max": 999.0, "count": 32 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29242.0, "min": 19623.0, "max": 33282.0, "count": 32 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5225179294745128, "min": -0.9998375517316163, "max": 1.6383333064690986, "count": 32 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 118.756398499012, "min": -31.99480165541172, "max": 162.19499734044075, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5225179294745128, "min": -0.9998375517316163, "max": 1.6383333064690986, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 118.756398499012, "min": -31.99480165541172, "max": 162.19499734044075, "count": 32 }, "Pyramids.Policy.RndReward.mean": { "value": 0.1282616472349335, "min": 0.10911554422151919, "max": 2.704905458725989, "count": 32 }, "Pyramids.Policy.RndReward.sum": { "value": 10.004408484324813, "min": 9.63618429331109, "max": 86.55697467923164, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687888663", "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 --resume", "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": "1687890831" }, "total": 2168.101467331, "count": 1, "self": 0.42950991799989424, "children": { "run_training.setup": { "total": 0.05721051800003352, "count": 1, "self": 0.05721051800003352 }, "TrainerController.start_learning": { "total": 2167.6147468950003, "count": 1, "self": 1.4878262110164542, "children": { "TrainerController._reset_env": { "total": 4.869165997000096, "count": 1, "self": 4.869165997000096 }, "TrainerController.advance": { "total": 2161.1573036179843, "count": 62564, "self": 1.3276581350623928, "children": { "env_step": { "total": 1534.914577863978, "count": 62564, "self": 1423.6765011559455, "children": { "SubprocessEnvManager._take_step": { "total": 110.4318620790134, "count": 62564, "self": 4.641679247993352, "children": { "TorchPolicy.evaluate": { "total": 105.79018283102005, "count": 61322, "self": 105.79018283102005 } } }, "workers": { "total": 0.8062146290189958, "count": 62564, "self": 0.0, "children": { "worker_root": { "total": 2162.4937484320003, "count": 62564, "is_parallel": true, "self": 851.0187111340174, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004159681000032833, "count": 1, "is_parallel": true, "self": 0.0022958350000408245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018638459999920087, "count": 8, "is_parallel": true, "self": 0.0018638459999920087 } } }, "UnityEnvironment.step": { "total": 0.05031853399998454, "count": 1, "is_parallel": true, "self": 0.0005899839999301548, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004735190000246803, "count": 1, "is_parallel": true, "self": 0.0004735190000246803 }, "communicator.exchange": { "total": 0.04741478599999027, "count": 1, "is_parallel": true, "self": 0.04741478599999027 }, "steps_from_proto": { "total": 0.001840245000039431, "count": 1, "is_parallel": true, "self": 0.0003960490000736172, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014441959999658138, "count": 8, "is_parallel": true, "self": 0.0014441959999658138 } } } } } } }, "UnityEnvironment.step": { "total": 1311.475037297983, "count": 62563, "is_parallel": true, "self": 32.429324028048995, "children": { "UnityEnvironment._generate_step_input": { "total": 21.93588839299366, "count": 62563, "is_parallel": true, "self": 21.93588839299366 }, "communicator.exchange": { "total": 1158.1839830619606, "count": 62563, "is_parallel": true, "self": 1158.1839830619606 }, "steps_from_proto": { "total": 98.92584181497989, "count": 62563, "is_parallel": true, "self": 19.40016254904458, "children": { "_process_rank_one_or_two_observation": { "total": 79.52567926593531, "count": 500504, "is_parallel": true, "self": 79.52567926593531 } } } } } } } } } } }, "trainer_advance": { "total": 624.9150676189439, "count": 62564, "self": 2.6092843859457844, "children": { "process_trajectory": { "total": 106.9724420670018, "count": 62564, "self": 106.7637397930016, "children": { "RLTrainer._checkpoint": { "total": 0.20870227400018848, "count": 2, "self": 0.20870227400018848 } } }, "_update_policy": { "total": 515.3333411659963, "count": 445, "self": 330.0105328459873, "children": { "TorchPPOOptimizer.update": { "total": 185.32280832000902, "count": 22302, "self": 185.32280832000902 } } } } } } }, "trainer_threads": { "total": 8.759998308960348e-07, "count": 1, "self": 8.759998308960348e-07 }, "TrainerController._save_models": { "total": 0.10045019299968772, "count": 1, "self": 0.0017624969996177242, "children": { "RLTrainer._checkpoint": { "total": 0.09868769600006999, "count": 1, "self": 0.09868769600006999 } } } } } } }