{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1565660834312439, "min": 0.1565660834312439, "max": 1.5110344886779785, "count": 166 }, "Pyramids.Policy.Entropy.sum": { "value": 4707.0029296875, "min": 4707.0029296875, "max": 45838.7421875, "count": 166 }, "Pyramids.Step.mean": { "value": 4979915.0, "min": 29896.0, "max": 4979915.0, "count": 166 }, "Pyramids.Step.sum": { "value": 4979915.0, "min": 29896.0, "max": 4979915.0, "count": 166 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7596249580383301, "min": -0.09912478178739548, "max": 0.8510122299194336, "count": 166 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 224.08937072753906, "min": -23.789947509765625, "max": 251.6753692626953, "count": 166 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006613036151975393, "min": -0.010047239251434803, "max": 0.41730430722236633, "count": 166 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.950845718383789, "min": -2.5319042205810547, "max": 98.901123046875, "count": 166 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06918241804227114, "min": 0.06377434989415286, "max": 0.0774429734715659, "count": 166 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9685538525917959, "min": 0.6041385523189573, "max": 1.1208737455502462, "count": 166 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.04013408112736856, "min": 0.00024820707498477806, "max": 0.05166137777930856, "count": 166 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5618771357831599, "min": 0.002978484899817337, "max": 0.7749206666896283, "count": 166 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.053942172528571e-06, "min": 2.053942172528571e-06, "max": 0.0002990583003139, "count": 166 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.8755190415399995e-05, "min": 2.8755190415399995e-05, "max": 0.00398644741118422, "count": 166 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10068461428571429, "min": 0.10068461428571429, "max": 0.19968610000000003, "count": 166 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4095846, "min": 1.4095846, "max": 2.82450166, "count": 166 }, "Pyramids.Policy.Beta.mean": { "value": 7.839296714285714e-05, "min": 7.839296714285714e-05, "max": 0.009968641390000001, "count": 166 }, "Pyramids.Policy.Beta.sum": { "value": 0.0010975015399999999, "min": 0.0010975015399999999, "max": 0.13288869642200002, "count": 166 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005115506239235401, "min": 0.004736213944852352, "max": 0.31785112619400024, "count": 166 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07161708921194077, "min": 0.06630699336528778, "max": 2.542809009552002, "count": 166 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 241.38709677419354, "min": 205.47972972972974, "max": 999.0, "count": 166 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29932.0, "min": 16567.0, "max": 34376.0, "count": 166 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.726343543358868, "min": -0.9999226331710815, "max": 1.7945202548761625, "count": 166 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 214.06659937649965, "min": -31.996001675724983, "max": 265.58899772167206, "count": 166 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.726343543358868, "min": -0.9999226331710815, "max": 1.7945202548761625, "count": 166 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 214.06659937649965, "min": -31.996001675724983, "max": 265.58899772167206, "count": 166 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013032083267849121, "min": 0.011718307633133451, "max": 5.836820939884467, "count": 166 }, "Pyramids.Policy.RndReward.sum": { "value": 1.615978325213291, "min": 1.4186316576087847, "max": 99.22595597803593, "count": 166 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 166 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 166 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1734987362", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735005229" }, "total": 17867.267364968004, "count": 1, "self": 0.8428121540055145, "children": { "run_training.setup": { "total": 0.08742685800098116, "count": 1, "self": 0.08742685800098116 }, "TrainerController.start_learning": { "total": 17866.337125955997, "count": 1, "self": 12.875868430684932, "children": { "TrainerController._reset_env": { "total": 3.051176987999497, "count": 1, "self": 3.051176987999497 }, "TrainerController.advance": { "total": 17850.31568798432, "count": 323137, "self": 13.148603702771652, "children": { "env_step": { "total": 12121.302369412471, "count": 323137, "self": 11261.368638919383, "children": { "SubprocessEnvManager._take_step": { "total": 852.5072753742788, "count": 323137, "self": 36.90964546420946, "children": { "TorchPolicy.evaluate": { "total": 815.5976299100694, "count": 312548, "self": 815.5976299100694 } } }, "workers": { "total": 7.426455118809827, "count": 323137, "self": 0.0, "children": { "worker_root": { "total": 17827.616065522045, "count": 323137, "is_parallel": true, "self": 7507.531310763992, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003829181001492543, "count": 1, "is_parallel": true, "self": 0.0012291770108276978, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026000039906648453, "count": 8, "is_parallel": true, "self": 0.0026000039906648453 } } }, "UnityEnvironment.step": { "total": 0.06282151399864233, "count": 1, "is_parallel": true, "self": 0.0008316169951285701, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005301090022840071, "count": 1, "is_parallel": true, "self": 0.0005301090022840071 }, "communicator.exchange": { "total": 0.05940465100138681, "count": 1, "is_parallel": true, "self": 0.05940465100138681 }, "steps_from_proto": { "total": 0.0020551369998429436, "count": 1, "is_parallel": true, "self": 0.00041780299943638965, "children": { "_process_rank_one_or_two_observation": { "total": 0.001637334000406554, "count": 8, "is_parallel": true, "self": 0.001637334000406554 } } } } } } }, "UnityEnvironment.step": { "total": 10320.084754758052, "count": 323136, "is_parallel": true, "self": 254.79581349675573, "children": { "UnityEnvironment._generate_step_input": { "total": 152.1197451789485, "count": 323136, "is_parallel": true, "self": 152.1197451789485 }, "communicator.exchange": { "total": 9243.167876113377, "count": 323136, "is_parallel": true, "self": 9243.167876113377 }, "steps_from_proto": { "total": 670.0013199689711, "count": 323136, "is_parallel": true, "self": 142.95692691750446, "children": { "_process_rank_one_or_two_observation": { "total": 527.0443930514666, "count": 2585088, "is_parallel": true, "self": 527.0443930514666 } } } } } } } } } } }, "trainer_advance": { "total": 5715.864714869076, "count": 323137, "self": 24.701568577238504, "children": { "process_trajectory": { "total": 884.9840235098454, "count": 323137, "self": 884.0035877718292, "children": { "RLTrainer._checkpoint": { "total": 0.9804357380162401, "count": 10, "self": 0.9804357380162401 } } }, "_update_policy": { "total": 4806.179122781992, "count": 2343, "self": 1923.9686476778588, "children": { "TorchPPOOptimizer.update": { "total": 2882.2104751041334, "count": 113877, "self": 2882.2104751041334 } } } } } } }, "trainer_threads": { "total": 1.0660005500540137e-06, "count": 1, "self": 1.0660005500540137e-06 }, "TrainerController._save_models": { "total": 0.09439148699311772, "count": 1, "self": 0.004332470991357695, "children": { "RLTrainer._checkpoint": { "total": 0.09005901600176003, "count": 1, "self": 0.09005901600176003 } } } } } } }