{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27946722507476807, "min": 0.27946722507476807, "max": 1.4223023653030396, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8495.8037109375, "min": 8495.8037109375, "max": 43146.96484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7026473879814148, "min": -0.11263036727905273, "max": 0.760591983795166, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 205.17303466796875, "min": -27.143918991088867, "max": 224.3746337890625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025793733075261116, "min": 0.00900337565690279, "max": 0.5020925402641296, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.5317702293396, "min": 2.5209450721740723, "max": 118.99592590332031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0703423618155493, "min": 0.06437795411847118, "max": 0.07471895710060031, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9847930654176903, "min": 0.5097872982950394, "max": 1.0711176672633098, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015261912029583843, "min": 0.0009527518301034166, "max": 0.015269969657224247, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2136667684141738, "min": 0.009766532110378118, "max": 0.22453860809522055, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.4479883266307144e-05, "min": 2.4479883266307144e-05, "max": 0.0009838354301878855, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0003427183657283, "min": 0.0003427183657283, "max": 0.011694330230567, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244797857142858, "min": 0.10244797857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342717, "min": 1.3886848, "max": 2.5694329999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025455305928571433, "min": 0.00025455305928571433, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003563742830000001, "min": 0.003563742830000001, "max": 0.1169663567, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010976001620292664, "min": 0.010976001620292664, "max": 0.5342116355895996, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1536640226840973, "min": 0.1536640226840973, "max": 3.7394814491271973, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 268.4424778761062, "min": 258.52100840336135, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30334.0, "min": 15984.0, "max": 33558.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7135553508996964, "min": -1.0000000521540642, "max": 1.7414705661915932, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 191.918199300766, "min": -30.510001733899117, "max": 207.23499737679958, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7135553508996964, "min": -1.0000000521540642, "max": 1.7414705661915932, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 191.918199300766, "min": -30.510001733899117, "max": 207.23499737679958, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030496460790995376, "min": 0.030496460790995376, "max": 10.688495183363557, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.415603608591482, "min": 3.415603608591482, "max": 171.0159229338169, "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": "1706877535", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706879884" }, "total": 2348.9017937430003, "count": 1, "self": 0.49208894500043243, "children": { "run_training.setup": { "total": 0.05560866000001852, "count": 1, "self": 0.05560866000001852 }, "TrainerController.start_learning": { "total": 2348.354096138, "count": 1, "self": 1.4720224579873502, "children": { "TrainerController._reset_env": { "total": 3.811920057000009, "count": 1, "self": 3.811920057000009 }, "TrainerController.advance": { "total": 2342.9729329700126, "count": 64399, "self": 1.5376919379555147, "children": { "env_step": { "total": 1705.4641717849822, "count": 64399, "self": 1566.3374322869417, "children": { "SubprocessEnvManager._take_step": { "total": 138.24776781801552, "count": 64399, "self": 5.029337689989688, "children": { "TorchPolicy.evaluate": { "total": 133.21843012802583, "count": 62553, "self": 133.21843012802583 } } }, "workers": { "total": 0.8789716800249607, "count": 64399, "self": 0.0, "children": { "worker_root": { "total": 2342.963256786994, "count": 64399, "is_parallel": true, "self": 901.8530679970054, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005564585999991323, "count": 1, "is_parallel": true, "self": 0.003567194999845924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019973910001453987, "count": 8, "is_parallel": true, "self": 0.0019973910001453987 } } }, "UnityEnvironment.step": { "total": 0.05456500899998673, "count": 1, "is_parallel": true, "self": 0.0006460450000531637, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005211519999761549, "count": 1, "is_parallel": true, "self": 0.0005211519999761549 }, "communicator.exchange": { "total": 0.05154936399998178, "count": 1, "is_parallel": true, "self": 0.05154936399998178 }, "steps_from_proto": { "total": 0.0018484479999756331, "count": 1, "is_parallel": true, "self": 0.00041580499998872256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014326429999869106, "count": 8, "is_parallel": true, "self": 0.0014326429999869106 } } } } } } }, "UnityEnvironment.step": { "total": 1441.1101887899886, "count": 64398, "is_parallel": true, "self": 36.31624070894054, "children": { "UnityEnvironment._generate_step_input": { "total": 25.8687088220276, "count": 64398, "is_parallel": true, "self": 25.8687088220276 }, "communicator.exchange": { "total": 1274.1377465600126, "count": 64398, "is_parallel": true, "self": 1274.1377465600126 }, "steps_from_proto": { "total": 104.78749269900771, "count": 64398, "is_parallel": true, "self": 21.54303588214816, "children": { "_process_rank_one_or_two_observation": { "total": 83.24445681685955, "count": 515184, "is_parallel": true, "self": 83.24445681685955 } } } } } } } } } } }, "trainer_advance": { "total": 635.9710692470746, "count": 64399, "self": 2.7693037440922126, "children": { "process_trajectory": { "total": 132.00520715498078, "count": 64399, "self": 131.8024335529808, "children": { "RLTrainer._checkpoint": { "total": 0.2027736019999793, "count": 2, "self": 0.2027736019999793 } } }, "_update_policy": { "total": 501.19655834800164, "count": 454, "self": 293.0172479730079, "children": { "TorchPPOOptimizer.update": { "total": 208.17931037499375, "count": 22833, "self": 208.17931037499375 } } } } } } }, "trainer_threads": { "total": 8.790002539171837e-07, "count": 1, "self": 8.790002539171837e-07 }, "TrainerController._save_models": { "total": 0.09721977399976822, "count": 1, "self": 0.0015638879999642086, "children": { "RLTrainer._checkpoint": { "total": 0.09565588599980401, "count": 1, "self": 0.09565588599980401 } } } } } } }