| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5403985381126404, |
| "min": 0.5403985381126404, |
| "max": 1.44121515750885, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 16272.4814453125, |
| "min": 16272.4814453125, |
| "max": 43720.703125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989927.0, |
| "min": 29888.0, |
| "max": 989927.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989927.0, |
| "min": 29888.0, |
| "max": 989927.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.33389392495155334, |
| "min": -0.11100856959819794, |
| "max": 0.3371206820011139, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 87.48020935058594, |
| "min": -26.86407470703125, |
| "max": 88.32562255859375, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.012724310159683228, |
| "min": 0.009730804711580276, |
| "max": 0.39708152413368225, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 3.3337693214416504, |
| "min": 2.56893253326416, |
| "max": 94.10832214355469, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06765708065473056, |
| "min": 0.06350068857623373, |
| "max": 0.07564422819375825, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.0148562098209584, |
| "min": 0.5193832203392582, |
| "max": 1.0148562098209584, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.013207582458914593, |
| "min": 7.937847550387263e-05, |
| "max": 0.015106858347255173, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.1981137368837189, |
| "min": 0.0009525417060464716, |
| "max": 0.21149601686157243, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.472757509113333e-06, |
| "min": 7.472757509113333e-06, |
| "max": 0.0002952356587309714, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00011209136263669999, |
| "min": 0.00011209136263669999, |
| "max": 0.0032248132250623, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10249088666666668, |
| "min": 0.10249088666666668, |
| "max": 0.19841188571428572, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.5373633000000002, |
| "min": 1.3888832, |
| "max": 2.3468782000000004, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025883957799999993, |
| "min": 0.00025883957799999993, |
| "max": 0.009841347382857144, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003882593669999999, |
| "min": 0.003882593669999999, |
| "max": 0.10750627623000002, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.014979460276663303, |
| "min": 0.014979460276663303, |
| "max": 0.4936983287334442, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.22469189763069153, |
| "min": 0.21537244319915771, |
| "max": 3.455888271331787, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 529.2166666666667, |
| "min": 501.3050847457627, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31753.0, |
| "min": 16559.0, |
| "max": 32913.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.2040532962729533, |
| "min": -0.999913385262092, |
| "max": 1.2952508202801316, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 72.2431977763772, |
| "min": -31.997201651334763, |
| "max": 77.87379860877991, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.2040532962729533, |
| "min": -0.999913385262092, |
| "max": 1.2952508202801316, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 72.2431977763772, |
| "min": -31.997201651334763, |
| "max": 77.87379860877991, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.08303417132628965, |
| "min": 0.07996101066533287, |
| "max": 9.223945077727823, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.982050279577379, |
| "min": 4.715128858333628, |
| "max": 156.807066321373, |
| "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": "1747854273", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "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": "2.7.0+cu126", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1747856414" |
| }, |
| "total": 2140.6219303319995, |
| "count": 1, |
| "self": 0.48419180599921674, |
| "children": { |
| "run_training.setup": { |
| "total": 0.02065920299901336, |
| "count": 1, |
| "self": 0.02065920299901336 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2140.1170793230012, |
| "count": 1, |
| "self": 1.4537158304883633, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.26621059900026, |
| "count": 1, |
| "self": 2.26621059900026 |
| }, |
| "TrainerController.advance": { |
| "total": 2136.3104784305124, |
| "count": 63235, |
| "self": 1.5808747191495058, |
| "children": { |
| "env_step": { |
| "total": 1460.2632387767608, |
| "count": 63235, |
| "self": 1298.3371825927334, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 161.03727307106965, |
| "count": 63235, |
| "self": 4.903382988724843, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 156.1338900823448, |
| "count": 62566, |
| "self": 156.1338900823448 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8887831129577535, |
| "count": 63235, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2134.774521999947, |
| "count": 63235, |
| "is_parallel": true, |
| "self": 954.4931254340026, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0020649150010285666, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006432160025724443, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014216989984561224, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014216989984561224 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04696811499889009, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000539730997843435, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004544020011962857, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004544020011962857 |
| }, |
| "communicator.exchange": { |
| "total": 0.044237596999664675, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.044237596999664675 |
| }, |
| "steps_from_proto": { |
| "total": 0.0017363850001856918, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003995400002168026, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013368449999688892, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013368449999688892 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1180.2813965659443, |
| "count": 63234, |
| "is_parallel": true, |
| "self": 32.441013105802995, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 23.6527423119187, |
| "count": 63234, |
| "is_parallel": true, |
| "self": 23.6527423119187 |
| }, |
| "communicator.exchange": { |
| "total": 1025.1679636810786, |
| "count": 63234, |
| "is_parallel": true, |
| "self": 1025.1679636810786 |
| }, |
| "steps_from_proto": { |
| "total": 99.01967746714399, |
| "count": 63234, |
| "is_parallel": true, |
| "self": 20.584476284957418, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 78.43520118218657, |
| "count": 505872, |
| "is_parallel": true, |
| "self": 78.43520118218657 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 674.4663649346021, |
| "count": 63235, |
| "self": 2.5474481838082284, |
| "children": { |
| "process_trajectory": { |
| "total": 129.60771117680088, |
| "count": 63235, |
| "self": 129.4076774558016, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2000337209992722, |
| "count": 2, |
| "self": 0.2000337209992722 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 542.311205573993, |
| "count": 432, |
| "self": 300.8728075799081, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 241.43839799408488, |
| "count": 22791, |
| "self": 241.43839799408488 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.919996616896242e-07, |
| "count": 1, |
| "self": 8.919996616896242e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08667357100057416, |
| "count": 1, |
| "self": 0.0012321909998718183, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08544138000070234, |
| "count": 1, |
| "self": 0.08544138000070234 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
