{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4349205493927002, "min": 0.4349205493927002, "max": 1.4509167671203613, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13026.740234375, "min": 13026.740234375, "max": 44015.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6068608164787292, "min": -0.08467353135347366, "max": 0.6359960436820984, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.74160766601562, "min": -20.406320571899414, "max": 179.98687744140625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011717760935425758, "min": 0.00023866606352385134, "max": 0.4801992177963257, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3161263465881348, "min": 0.06587183475494385, "max": 113.80721282958984, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07056322113272646, "min": 0.06579151245144506, "max": 0.07319928155976371, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9878850958581705, "min": 0.4950094183187011, "max": 1.0559010526242976, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015314468134117005, "min": 0.0007976477274245678, "max": 0.01775806937939833, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21440255387763807, "min": 0.0055835340919719745, "max": 0.24889251725107894, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.423790382578577e-06, "min": 7.423790382578577e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010393306535610007, "min": 0.00010393306535610007, "max": 0.0035082899305700996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024745642857143, "min": 0.1024745642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346439000000002, "min": 1.3691136000000002, "max": 2.5694299, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025720897214285735, "min": 0.00025720897214285735, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036009256100000032, "min": 0.0036009256100000032, "max": 0.11696604701, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012180037796497345, "min": 0.012180037796497345, "max": 0.5943782925605774, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17052052915096283, "min": 0.17052052915096283, "max": 4.160647869110107, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.1875, "min": 301.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 15984.0, "max": 32863.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6044562332487355, "min": -1.0000000521540642, "max": 1.678923695818665, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 154.0277983918786, "min": -32.000001668930054, "max": 162.85559849441051, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6044562332487355, "min": -1.0000000521540642, "max": 1.678923695818665, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 154.0277983918786, "min": -32.000001668930054, "max": 162.85559849441051, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03963329741175888, "min": 0.03963329741175888, "max": 12.655772911384702, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8047965515288524, "min": 3.8047965515288524, "max": 202.49236658215523, "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": "1738684439", "python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738686123" }, "total": 1683.786153886, "count": 1, "self": 0.37264405099972464, "children": { "run_training.setup": { "total": 0.02198454400013361, "count": 1, "self": 0.02198454400013361 }, "TrainerController.start_learning": { "total": 1683.391525291, "count": 1, "self": 1.2434760490152712, "children": { "TrainerController._reset_env": { "total": 2.0830961080000634, "count": 1, "self": 2.0830961080000634 }, "TrainerController.advance": { "total": 1679.9796257229852, "count": 63910, "self": 1.2136569989970667, "children": { "env_step": { "total": 1049.4589806350161, "count": 63910, "self": 908.0483304490085, "children": { "SubprocessEnvManager._take_step": { "total": 140.6643626380046, "count": 63910, "self": 4.194814932022155, "children": { "TorchPolicy.evaluate": { "total": 136.46954770598245, "count": 62568, "self": 136.46954770598245 } } }, "workers": { "total": 0.7462875480030107, "count": 63910, "self": 0.0, "children": { "worker_root": { "total": 1681.3346398369995, "count": 63910, "is_parallel": true, "self": 862.3611900880353, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019269919998805562, "count": 1, "is_parallel": true, "self": 0.0006715769993661524, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012554150005144038, "count": 8, "is_parallel": true, "self": 0.0012554150005144038 } } }, "UnityEnvironment.step": { "total": 0.03536709500008328, "count": 1, "is_parallel": true, "self": 0.0003533659998993244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002988649998769688, "count": 1, "is_parallel": true, "self": 0.0002988649998769688 }, "communicator.exchange": { "total": 0.033653367000169965, "count": 1, "is_parallel": true, "self": 0.033653367000169965 }, "steps_from_proto": { "total": 0.0010614970001370239, "count": 1, "is_parallel": true, "self": 0.0002519240001674916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008095729999695322, "count": 8, "is_parallel": true, "self": 0.0008095729999695322 } } } } } } }, "UnityEnvironment.step": { "total": 818.9734497489642, "count": 63909, "is_parallel": true, "self": 19.91374336492754, "children": { "UnityEnvironment._generate_step_input": { "total": 13.562326243004918, "count": 63909, "is_parallel": true, "self": 13.562326243004918 }, "communicator.exchange": { "total": 725.7001272350135, "count": 63909, "is_parallel": true, "self": 725.7001272350135 }, "steps_from_proto": { "total": 59.79725290601823, "count": 63909, "is_parallel": true, "self": 13.061642048182648, "children": { "_process_rank_one_or_two_observation": { "total": 46.73561085783558, "count": 511272, "is_parallel": true, "self": 46.73561085783558 } } } } } } } } } } }, "trainer_advance": { "total": 629.306988088972, "count": 63910, "self": 2.4319671599464527, "children": { "process_trajectory": { "total": 116.65023003202623, "count": 63910, "self": 116.45127013402634, "children": { "RLTrainer._checkpoint": { "total": 0.19895989799988456, "count": 2, "self": 0.19895989799988456 } } }, "_update_policy": { "total": 510.22479089699937, "count": 451, "self": 277.1719343429768, "children": { "TorchPPOOptimizer.update": { "total": 233.05285655402258, "count": 22806, "self": 233.05285655402258 } } } } } } }, "trainer_threads": { "total": 1.014999725157395e-06, "count": 1, "self": 1.014999725157395e-06 }, "TrainerController._save_models": { "total": 0.0853263959998003, "count": 1, "self": 0.0014671939998152084, "children": { "RLTrainer._checkpoint": { "total": 0.08385920199998509, "count": 1, "self": 0.08385920199998509 } } } } } } }