| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.07561375200748444, |
| "min": 0.07561375200748444, |
| "max": 1.4175474643707275, |
| "count": 333 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 2290.189208984375, |
| "min": 2277.609375, |
| "max": 43002.71875, |
| "count": 333 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 9989990.0, |
| "min": 29952.0, |
| "max": 9989990.0, |
| "count": 333 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 9989990.0, |
| "min": 29952.0, |
| "max": 9989990.0, |
| "count": 333 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8543348908424377, |
| "min": -0.09571170061826706, |
| "max": 1.001431941986084, |
| "count": 333 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 266.552490234375, |
| "min": -22.683673858642578, |
| "max": 321.45965576171875, |
| "count": 333 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.0060005029663443565, |
| "min": -0.05893249437212944, |
| "max": 0.39971691370010376, |
| "count": 333 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.8721568584442139, |
| "min": -16.913625717163086, |
| "max": 94.73291015625, |
| "count": 333 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06753605802200084, |
| "min": 0.06181583571120907, |
| "max": 0.07418865210020933, |
| "count": 333 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9455048123080119, |
| "min": 0.5193205647014654, |
| "max": 1.102130610325748, |
| "count": 333 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.016244731489171115, |
| "min": 0.001776320314338212, |
| "max": 0.01687595542713169, |
| "count": 333 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.22742624084839563, |
| "min": 0.021315843772058543, |
| "max": 0.24031729904555843, |
| "count": 333 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.573447475850008e-07, |
| "min": 7.573447475850008e-07, |
| "max": 0.0002995150630187886, |
| "count": 333 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 1.0602826466190011e-05, |
| "min": 1.0602826466190011e-05, |
| "max": 0.0043448526517158, |
| "count": 333 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.100252415, |
| "min": 0.100252415, |
| "max": 0.1998383542857143, |
| "count": 333 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4035338099999999, |
| "min": 1.3988684800000002, |
| "max": 2.9482842, |
| "count": 333 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 3.521625850000003e-05, |
| "min": 3.521625850000003e-05, |
| "max": 0.009983851593142858, |
| "count": 333 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0004930276190000004, |
| "min": 0.0004930276190000004, |
| "max": 0.14483359158000003, |
| "count": 333 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.004874624777585268, |
| "min": 0.004479951225221157, |
| "max": 0.4924687445163727, |
| "count": 333 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.06824474781751633, |
| "min": 0.06451395899057388, |
| "max": 3.4472811222076416, |
| "count": 333 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 188.7391304347826, |
| "min": 170.9467455621302, |
| "max": 999.0, |
| "count": 333 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30387.0, |
| "min": 15984.0, |
| "max": 32841.0, |
| "count": 333 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7615540238178296, |
| "min": -1.0000000521540642, |
| "max": 1.8290532443826721, |
| "count": 333 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 283.61019783467054, |
| "min": -28.230001620948315, |
| "max": 317.45419831573963, |
| "count": 333 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7615540238178296, |
| "min": -1.0000000521540642, |
| "max": 1.8290532443826721, |
| "count": 333 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 283.61019783467054, |
| "min": -28.230001620948315, |
| "max": 317.45419831573963, |
| "count": 333 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.009537448053684242, |
| "min": 0.00889705627450894, |
| "max": 9.711620643734932, |
| "count": 333 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.535529136643163, |
| "min": 1.293063686684036, |
| "max": 155.3859302997589, |
| "count": 333 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 333 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 333 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1777833496", |
| "python_version": "3.10.19 (main, May 3 2026, 16:56:55) [GCC 15.2.1 20260209]", |
| "command_line_arguments": "/home/lyra/.venvs/mlagents-env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 3 --no-graphics", |
| "mlagents_version": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1777840569" |
| }, |
| "total": 7073.488069977, |
| "count": 1, |
| "self": 0.2192988750175573, |
| "children": { |
| "run_training.setup": { |
| "total": 0.014218403986888006, |
| "count": 1, |
| "self": 0.014218403986888006 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7073.254552697996, |
| "count": 1, |
| "self": 5.098532143427292, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.2851067570154555, |
| "count": 1, |
| "self": 1.2851067570154555 |
| }, |
| "TrainerController.advance": { |
| "total": 7066.834196417563, |
| "count": 659781, |
| "self": 5.049942689278396, |
| "children": { |
| "env_step": { |
| "total": 4363.827563082683, |
| "count": 659781, |
| "self": 3845.6388522846974, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 514.9294849102444, |
| "count": 659781, |
| "self": 17.37210873494041, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 497.55737617530394, |
| "count": 625071, |
| "self": 497.55737617530394 |
| } |
| } |
| }, |
| "workers": { |
| "total": 3.259225887741195, |
| "count": 659781, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7064.612573969818, |
| "count": 659781, |
| "is_parallel": true, |
| "self": 3585.5642767888203, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0010457699827384204, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003072059771511704, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.00073856400558725, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.00073856400558725 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.014706980990013108, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0001484189706388861, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00017089801258407533, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00017089801258407533 |
| }, |
| "communicator.exchange": { |
| "total": 0.013944778009317815, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.013944778009317815 |
| }, |
| "steps_from_proto": { |
| "total": 0.00044288599747233093, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00011334801092743874, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0003295379865448922, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0003295379865448922 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 3479.048297180998, |
| "count": 659780, |
| "is_parallel": true, |
| "self": 86.30336274029105, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 55.967362358642276, |
| "count": 659780, |
| "is_parallel": true, |
| "self": 55.967362358642276 |
| }, |
| "communicator.exchange": { |
| "total": 3095.671771015768, |
| "count": 659780, |
| "is_parallel": true, |
| "self": 3095.671771015768 |
| }, |
| "steps_from_proto": { |
| "total": 241.1058010662964, |
| "count": 659780, |
| "is_parallel": true, |
| "self": 52.665990547364345, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 188.43981051893206, |
| "count": 5278240, |
| "is_parallel": true, |
| "self": 188.43981051893206 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 2697.956690645602, |
| "count": 659781, |
| "self": 9.748778851353563, |
| "children": { |
| "process_trajectory": { |
| "total": 542.5550146230671, |
| "count": 659781, |
| "self": 541.7881467191328, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.766867903934326, |
| "count": 20, |
| "self": 0.766867903934326 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 2145.6528971711814, |
| "count": 4719, |
| "self": 1277.2010323219874, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 868.451864849194, |
| "count": 227991, |
| "self": 868.451864849194 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 4.899920895695686e-07, |
| "count": 1, |
| "self": 4.899920895695686e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.036716889997478575, |
| "count": 1, |
| "self": 0.0008008040022104979, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.03591608599526808, |
| "count": 1, |
| "self": 0.03591608599526808 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
