{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16183078289031982, "min": 0.16183078289031982, "max": 0.19563491642475128, "count": 11 }, "Pyramids.Policy.Entropy.sum": { "value": 4857.5126953125, "min": 4857.5126953125, "max": 5840.8759765625, "count": 11 }, "Pyramids.Step.mean": { "value": 3329990.0, "min": 3029892.0, "max": 3329990.0, "count": 11 }, "Pyramids.Step.sum": { "value": 3329990.0, "min": 3029892.0, "max": 3329990.0, "count": 11 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7569361329078674, "min": 0.6572807431221008, "max": 0.8241286277770996, "count": 11 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 223.29615783691406, "min": 184.69589233398438, "max": 249.71096801757812, "count": 11 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008521034382283688, "min": -0.002375907264649868, "max": 0.010143999010324478, "count": 11 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.513705253601074, "min": -0.7198998928070068, "max": 2.9924798011779785, "count": 11 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 242.45378151260505, "min": 226.7923076923077, "max": 298.35353535353534, "count": 11 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28852.0, "min": 26690.0, "max": 31380.0, "count": 11 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7085299838334322, "min": 1.641022202643481, "max": 1.7736259428144412, "count": 11 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.02359806001186, "min": 162.46119806170464, "max": 232.3449985086918, "count": 11 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7085299838334322, "min": 1.641022202643481, "max": 1.7736259428144412, "count": 11 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.02359806001186, "min": 162.46119806170464, "max": 232.3449985086918, "count": 11 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02120728931058693, "min": 0.020747624346282145, "max": 0.027397025733888667, "count": 11 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5448747172704316, "min": 2.4354529173870105, "max": 2.9356366415158845, "count": 11 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07088167101336534, "min": 0.06472716507241351, "max": 0.072778828392449, "count": 11 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0632250652004802, "min": 0.9061803110137892, "max": 1.0632250652004802, "count": 11 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015138761240424396, "min": 0.01235295686984457, "max": 0.015479897946490727, "count": 11 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22708141860636594, "min": 0.17294139617782398, "max": 0.22708141860636594, "count": 11 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.584155186237143e-05, "min": 1.584155186237143e-05, "max": 4.150687391950612e-05, "count": 11 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00023762327793557143, "min": 0.00023762327793557143, "max": 0.0005810962348730857, "count": 11 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10528048571428572, "min": 0.10528048571428572, "max": 0.11383559591836735, "count": 11 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5792072857142858, "min": 1.4862316000000002, "max": 1.643657685714286, "count": 11 }, "Pyramids.Policy.Beta.mean": { "value": 0.000537520522857143, "min": 0.000537520522857143, "max": 0.0013921760322448981, "count": 11 }, "Pyramids.Policy.Beta.sum": { "value": 0.008062807842857145, "min": 0.008062807842857145, "max": 0.019490464451428574, "count": 11 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008326766081154346, "min": 0.008326766081154346, "max": 0.009064115583896637, "count": 11 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12490149587392807, "min": 0.12157151103019714, "max": 0.13421687483787537, "count": 11 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 11 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 11 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1688730910", "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": "1688731874" }, "total": 963.2737938869996, "count": 1, "self": 0.28846379599963257, "children": { "run_training.setup": { "total": 0.0411267620002036, "count": 1, "self": 0.0411267620002036 }, "TrainerController.start_learning": { "total": 962.9442033289997, "count": 1, "self": 0.6229140661216661, "children": { "TrainerController._reset_env": { "total": 4.1584555089993955, "count": 1, "self": 4.1584555089993955 }, "TrainerController.advance": { "total": 957.9727760298774, "count": 22002, "self": 0.6274250227652374, "children": { "env_step": { "total": 730.2751400471425, "count": 22002, "self": 685.6130119412119, "children": { "SubprocessEnvManager._take_step": { "total": 44.30485008307005, "count": 22002, "self": 1.9146209049231402, "children": { "TorchPolicy.evaluate": { "total": 42.39022917814691, "count": 20933, "self": 42.39022917814691 } } }, "workers": { "total": 0.3572780228605552, "count": 22002, "self": 0.0, "children": { "worker_root": { "total": 959.8345618770909, "count": 22002, "is_parallel": true, "self": 321.63205124029446, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001999586000238196, "count": 1, "is_parallel": true, "self": 0.0006654319986409973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013341540015971987, "count": 8, "is_parallel": true, "self": 0.0013341540015971987 } } }, "UnityEnvironment.step": { "total": 0.055308815999524086, "count": 1, "is_parallel": true, "self": 0.0006113979998190189, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005261489986878587, "count": 1, "is_parallel": true, "self": 0.0005261489986878587 }, "communicator.exchange": { "total": 0.052172805000736844, "count": 1, "is_parallel": true, "self": 0.052172805000736844 }, "steps_from_proto": { "total": 0.0019984640002803644, "count": 1, "is_parallel": true, "self": 0.00040776100286166184, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015907029974187026, "count": 8, "is_parallel": true, "self": 0.0015907029974187026 } } } } } } }, "UnityEnvironment.step": { "total": 638.2025106367964, "count": 22001, "is_parallel": true, "self": 12.518055500813716, "children": { "UnityEnvironment._generate_step_input": { "total": 8.825988795009835, "count": 22001, "is_parallel": true, "self": 8.825988795009835 }, "communicator.exchange": { "total": 576.9878752659479, "count": 22001, "is_parallel": true, "self": 576.9878752659479 }, "steps_from_proto": { "total": 39.870591075025004, "count": 22001, "is_parallel": true, "self": 8.422388295182827, "children": { "_process_rank_one_or_two_observation": { "total": 31.448202779842177, "count": 176008, "is_parallel": true, "self": 31.448202779842177 } } } } } } } } } } }, "trainer_advance": { "total": 227.0702109599697, "count": 22002, "self": 1.132208885936052, "children": { "process_trajectory": { "total": 42.091502506016695, "count": 22002, "self": 42.091502506016695 }, "_update_policy": { "total": 183.84649956801695, "count": 158, "self": 116.91646065898931, "children": { "TorchPPOOptimizer.update": { "total": 66.93003890902764, "count": 7590, "self": 66.93003890902764 } } } } } } }, "trainer_threads": { "total": 1.3980006769998e-06, "count": 1, "self": 1.3980006769998e-06 }, "TrainerController._save_models": { "total": 0.19005632600055833, "count": 1, "self": 0.003046071000426309, "children": { "RLTrainer._checkpoint": { "total": 0.18701025500013202, "count": 1, "self": 0.18701025500013202 } } } } } } }