{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32781553268432617, "min": 0.3253123164176941, "max": 1.3918181657791138, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 16380.2861328125, "min": 16286.4365234375, "max": 70481.671875, "count": 20 }, "Pyramids.Step.mean": { "value": 999907.0, "min": 49940.0, "max": 999907.0, "count": 20 }, "Pyramids.Step.sum": { "value": 999907.0, "min": 49940.0, "max": 999907.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5820431113243103, "min": -0.09353125095367432, "max": 0.5820431113243103, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 272.39617919921875, "min": -37.3189697265625, "max": 272.39617919921875, "count": 20 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0013404717901721597, "min": -0.0013404717901721597, "max": 0.1490127593278885, "count": 20 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.6273407936096191, "min": -0.6273407936096191, "max": 59.45608901977539, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06826182905216768, "min": 0.0674683024973728, "max": 0.0750626987207472, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.5700220681998567, "min": 1.0508777820904607, "max": 1.7042978857352864, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016236349299172132, "min": 0.0007544503207537186, "max": 0.01709986551910345, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.37343603388095903, "min": 0.014334556094320652, "max": 0.41039677245848283, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.488293156108696e-06, "min": 7.488293156108696e-06, "max": 0.0002917177313321857, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001722307425905, "min": 0.0001722307425905, "max": 0.005782599272467, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024960652173913, "min": 0.1024960652173913, "max": 0.19723924285714287, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3574094999999997, "min": 2.3574094999999997, "max": 4.198168300000001, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025935691521739127, "min": 0.00025935691521739127, "max": 0.009724200361428572, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.00596520905, "min": 0.00596520905, "max": 0.19278054670000003, "count": 20 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011381903663277626, "min": 0.011381903663277626, "max": 0.2891659140586853, "count": 20 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.26178377866744995, "min": 0.26178377866744995, "max": 4.048322677612305, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 326.7105263157895, "min": 320.9868421052632, "max": 996.7916666666666, "count": 20 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 49660.0, "min": 47332.0, "max": 52418.0, "count": 20 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5936378930616224, "min": -0.9560250515739123, "max": 1.6391945012322027, "count": 20 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 243.8265976384282, "min": -45.88920247554779, "max": 244.15239719301462, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5936378930616224, "min": -0.9560250515739123, "max": 1.6391945012322027, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 243.8265976384282, "min": -45.88920247554779, "max": 244.15239719301462, "count": 20 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03852816585947271, "min": 0.03852816585947271, "max": 4.113878913378964, "count": 20 }, "Pyramids.Policy.RndReward.sum": { "value": 5.894809376499325, "min": 5.894809376499325, "max": 197.46618784219027, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1673451998", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673454028" }, "total": 2030.5010344799994, "count": 1, "self": 0.42465911699855496, "children": { "run_training.setup": { "total": 0.11476273100015533, "count": 1, "self": 0.11476273100015533 }, "TrainerController.start_learning": { "total": 2029.9616126320007, "count": 1, "self": 1.159215314958601, "children": { "TrainerController._reset_env": { "total": 6.33323344100063, "count": 1, "self": 6.33323344100063 }, "TrainerController.advance": { "total": 2022.3839513910416, "count": 64010, "self": 1.1557232457798818, "children": { "env_step": { "total": 1367.5589351991312, "count": 64010, "self": 1268.4804875791106, "children": { "SubprocessEnvManager._take_step": { "total": 98.32118079104566, "count": 64010, "self": 4.1303473940051845, "children": { "TorchPolicy.evaluate": { "total": 94.19083339704048, "count": 62554, "self": 31.69221802514039, "children": { "TorchPolicy.sample_actions": { "total": 62.49861537190009, "count": 62554, "self": 62.49861537190009 } } } } }, "workers": { "total": 0.7572668289749345, "count": 64010, "self": 0.0, "children": { "worker_root": { "total": 2025.8349935890874, "count": 64010, "is_parallel": true, "self": 850.7980731320586, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018750139997791848, "count": 1, "is_parallel": true, "self": 0.0006027170011293492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012722969986498356, "count": 8, "is_parallel": true, "self": 0.0012722969986498356 } } }, "UnityEnvironment.step": { "total": 0.04477921400030027, "count": 1, "is_parallel": true, "self": 0.000475162000839191, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004152269993937807, "count": 1, "is_parallel": true, "self": 0.0004152269993937807 }, "communicator.exchange": { "total": 0.04232807500011404, "count": 1, "is_parallel": true, "self": 0.04232807500011404 }, "steps_from_proto": { "total": 0.0015607499999532592, "count": 1, "is_parallel": true, "self": 0.00039217400080815423, "children": { "_process_rank_one_or_two_observation": { "total": 0.001168575999145105, "count": 8, "is_parallel": true, "self": 0.001168575999145105 } } } } } } }, "UnityEnvironment.step": { "total": 1175.0369204570288, "count": 64009, "is_parallel": true, "self": 27.37322329003382, "children": { "UnityEnvironment._generate_step_input": { "total": 21.81983024096553, "count": 64009, "is_parallel": true, "self": 21.81983024096553 }, "communicator.exchange": { "total": 1029.4639337190629, "count": 64009, "is_parallel": true, "self": 1029.4639337190629 }, "steps_from_proto": { "total": 96.3799332069666, "count": 64009, "is_parallel": true, "self": 21.112935729001947, "children": { "_process_rank_one_or_two_observation": { "total": 75.26699747796465, "count": 512072, "is_parallel": true, "self": 75.26699747796465 } } } } } } } } } } }, "trainer_advance": { "total": 653.6692929461306, "count": 64010, "self": 2.1772219230997507, "children": { "process_trajectory": { "total": 142.66140216603435, "count": 64010, "self": 142.4697971240348, "children": { "RLTrainer._checkpoint": { "total": 0.1916050419995372, "count": 2, "self": 0.1916050419995372 } } }, "_update_policy": { "total": 508.83066885699645, "count": 456, "self": 195.29943234804978, "children": { "TorchPPOOptimizer.update": { "total": 313.5312365089467, "count": 22791, "self": 313.5312365089467 } } } } } } }, "trainer_threads": { "total": 9.189998309011571e-07, "count": 1, "self": 9.189998309011571e-07 }, "TrainerController._save_models": { "total": 0.08521156599999813, "count": 1, "self": 0.001373162999698252, "children": { "RLTrainer._checkpoint": { "total": 0.08383840300029988, "count": 1, "self": 0.08383840300029988 } } } } } } }