| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.17398707568645477, |
| "min": 0.1654859483242035, |
| "max": 1.4028334617614746, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5208.47705078125, |
| "min": 5006.94287109375, |
| "max": 42556.35546875, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999896.0, |
| "min": 29952.0, |
| "max": 2999896.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999896.0, |
| "min": 29952.0, |
| "max": 2999896.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7487068772315979, |
| "min": -0.16433028876781464, |
| "max": 0.7487068772315979, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 215.62757873535156, |
| "min": -39.76792907714844, |
| "max": 215.62757873535156, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.0075357044115662575, |
| "min": -0.019513145089149475, |
| "max": 0.44401195645332336, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 2.1702828407287598, |
| "min": -5.541733264923096, |
| "max": 105.2308349609375, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06487057891527434, |
| "min": 0.06318015543481788, |
| "max": 0.07273508993584626, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9081881048138407, |
| "min": 0.4957247238461365, |
| "max": 1.091026349037694, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014487407694105059, |
| "min": 0.0006884899445196451, |
| "max": 0.014487407694105059, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20282370771747082, |
| "min": 0.008207219881288964, |
| "max": 0.20846094469986082, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.5229352066738101e-06, |
| "min": 1.5229352066738101e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.132109289343334e-05, |
| "min": 2.132109289343334e-05, |
| "max": 0.004011046662984466, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10050761190476191, |
| "min": 0.10050761190476191, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.407106566666667, |
| "min": 1.3962282666666668, |
| "max": 2.737533533333334, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.0710429285714317e-05, |
| "min": 6.0710429285714317e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008499460100000005, |
| "min": 0.0008499460100000005, |
| "max": 0.13370785178, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.004386597312986851, |
| "min": 0.003907230217009783, |
| "max": 0.6584237813949585, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.06141236051917076, |
| "min": 0.054701223969459534, |
| "max": 4.60896635055542, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 273.6140350877193, |
| "min": 267.59090909090907, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31192.0, |
| "min": 15984.0, |
| "max": 32844.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6912877009364597, |
| "min": -1.0000000521540642, |
| "max": 1.7324090746316043, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 192.8067979067564, |
| "min": -31.998801678419113, |
| "max": 192.8067979067564, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6912877009364597, |
| "min": -1.0000000521540642, |
| "max": 1.7324090746316043, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 192.8067979067564, |
| "min": -31.998801678419113, |
| "max": 192.8067979067564, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.012387844743978093, |
| "min": 0.011444025801029056, |
| "max": 13.01464618369937, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.4122143008135026, |
| "min": 1.160592756317783, |
| "max": 208.2343389391899, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1741749150", |
| "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 Training2 --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": "1741756440" |
| }, |
| "total": 7289.855089797, |
| "count": 1, |
| "self": 0.5269190419985534, |
| "children": { |
| "run_training.setup": { |
| "total": 0.02179721500033338, |
| "count": 1, |
| "self": 0.02179721500033338 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7289.306373540001, |
| "count": 1, |
| "self": 5.112466279403634, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.237583170999642, |
| "count": 1, |
| "self": 2.237583170999642 |
| }, |
| "TrainerController.advance": { |
| "total": 7281.863593620598, |
| "count": 193640, |
| "self": 4.749025777969109, |
| "children": { |
| "env_step": { |
| "total": 5170.747577852345, |
| "count": 193640, |
| "self": 4666.061135549464, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 501.88766075899366, |
| "count": 193640, |
| "self": 15.108762485664556, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 486.7788982733291, |
| "count": 187565, |
| "self": 486.7788982733291 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.7987815438868893, |
| "count": 193640, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7272.484765575033, |
| "count": 193640, |
| "is_parallel": true, |
| "self": 2978.223463106262, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.003106922999904782, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000931412000227283, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002175510999677499, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002175510999677499 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05038083900035417, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000541247000455769, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0005062840000391589, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005062840000391589 |
| }, |
| "communicator.exchange": { |
| "total": 0.04769549799993911, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04769549799993911 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016378099999201368, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003444789995228348, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001293331000397302, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001293331000397302 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4294.261302468771, |
| "count": 193639, |
| "is_parallel": true, |
| "self": 98.51436699385522, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 72.69923131639962, |
| "count": 193639, |
| "is_parallel": true, |
| "self": 72.69923131639962 |
| }, |
| "communicator.exchange": { |
| "total": 3817.28920070833, |
| "count": 193639, |
| "is_parallel": true, |
| "self": 3817.28920070833 |
| }, |
| "steps_from_proto": { |
| "total": 305.75850345018625, |
| "count": 193639, |
| "is_parallel": true, |
| "self": 64.14307960454835, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 241.6154238456379, |
| "count": 1549112, |
| "is_parallel": true, |
| "self": 241.6154238456379 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 2106.3669899902843, |
| "count": 193640, |
| "self": 9.470331218572937, |
| "children": { |
| "process_trajectory": { |
| "total": 411.50425770971015, |
| "count": 193640, |
| "self": 410.8936626067107, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.6105951029994685, |
| "count": 6, |
| "self": 0.6105951029994685 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1685.3924010620012, |
| "count": 1398, |
| "self": 918.6039301837045, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 766.7884708782967, |
| "count": 68322, |
| "self": 766.7884708782967 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.33999365568161e-07, |
| "count": 1, |
| "self": 8.33999365568161e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09272963500006881, |
| "count": 1, |
| "self": 0.0014833410004939651, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09124629399957485, |
| "count": 1, |
| "self": 0.09124629399957485 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
