Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[BugFix] Fix strict_length=True in SliceSampler #2037

Merged
merged 2 commits into from
Mar 24, 2024
Merged

[BugFix] Fix strict_length=True in SliceSampler #2037

merged 2 commits into from
Mar 24, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Mar 23, 2024 •
edited
Loading

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Mar 23, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2037

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure

As of commit fac7496 with merge base cd540bf (image):

NEW FAILURE - The following job has failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Mar 23, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 23, 2024 •
edited
Loading

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests

Total Benchmarks: 91. Improved: $\large\color{#35bf28}6$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 55.6630ms 53.7039ms 18.6206 Ops/s 17.9162 Ops/s $\color{#35bf28}+3.93\%$
test_sync 41.6727ms 30.8061ms 32.4611 Ops/s 32.0298 Ops/s $\color{#35bf28}+1.35\%$
test_async 42.8357ms 28.9027ms 34.5988 Ops/s 35.2467 Ops/s $\color{#d91a1a}-1.84\%$
test_simple 0.3233s 0.3215s 3.1106 Ops/s 2.9879 Ops/s $\color{#35bf28}+4.11\%$
test_transformed 0.5168s 0.4670s 2.1415 Ops/s 2.1491 Ops/s $\color{#d91a1a}-0.35\%$
test_serial 1.2338s 1.1813s 0.8465 Ops/s 0.8567 Ops/s $\color{#d91a1a}-1.20\%$
test_parallel 1.0742s 1.0220s 0.9785 Ops/s 0.9673 Ops/s $\color{#35bf28}+1.16\%$
test_step_mdp_speed[True-True-True-True-True] 0.1173ms 21.5476μs 46.4089 KOps/s 47.7071 KOps/s $\color{#d91a1a}-2.72\%$
test_step_mdp_speed[True-True-True-True-False] 40.6850μs 12.9890μs 76.9881 KOps/s 77.6446 KOps/s $\color{#d91a1a}-0.85\%$
test_step_mdp_speed[True-True-True-False-True] 40.0750μs 12.6560μs 79.0140 KOps/s 80.8119 KOps/s $\color{#d91a1a}-2.22\%$
test_step_mdp_speed[True-True-True-False-False] 30.4870μs 7.6184μs 131.2609 KOps/s 133.1907 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[True-True-False-True-True] 53.9400μs 22.8581μs 43.7481 KOps/s 44.9618 KOps/s $\color{#d91a1a}-2.70\%$
test_step_mdp_speed[True-True-False-True-False] 40.3140μs 14.2807μs 70.0246 KOps/s 70.3293 KOps/s $\color{#d91a1a}-0.43\%$
test_step_mdp_speed[True-True-False-False-True] 66.4930μs 13.9143μs 71.8686 KOps/s 72.9350 KOps/s $\color{#d91a1a}-1.46\%$
test_step_mdp_speed[True-True-False-False-False] 32.6110μs 8.8402μs 113.1191 KOps/s 113.8656 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-False-True-True-True] 73.4130μs 24.0163μs 41.6384 KOps/s 41.6377 KOps/s $+0.00\%$
test_step_mdp_speed[True-False-True-True-False] 51.7660μs 15.4620μs 64.6745 KOps/s 64.7970 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[True-False-True-False-True] 41.6570μs 13.6388μs 73.3200 KOps/s 73.6285 KOps/s $\color{#d91a1a}-0.42\%$
test_step_mdp_speed[True-False-True-False-False] 33.7030μs 8.7738μs 113.9756 KOps/s 114.2462 KOps/s $\color{#d91a1a}-0.24\%$
test_step_mdp_speed[True-False-False-True-True] 51.2560μs 25.2576μs 39.5921 KOps/s 40.2254 KOps/s $\color{#d91a1a}-1.57\%$
test_step_mdp_speed[True-False-False-True-False] 38.4520μs 16.7545μs 59.6853 KOps/s 60.2026 KOps/s $\color{#d91a1a}-0.86\%$
test_step_mdp_speed[True-False-False-False-True] 48.8410μs 14.9740μs 66.7823 KOps/s 67.4566 KOps/s $\color{#d91a1a}-1.00\%$
test_step_mdp_speed[True-False-False-False-False] 42.2680μs 10.0186μs 99.8148 KOps/s 100.1893 KOps/s $\color{#d91a1a}-0.37\%$
test_step_mdp_speed[False-True-True-True-True] 47.5990μs 24.4761μs 40.8561 KOps/s 41.8219 KOps/s $\color{#d91a1a}-2.31\%$
test_step_mdp_speed[False-True-True-True-False] 60.4620μs 15.7347μs 63.5539 KOps/s 64.1904 KOps/s $\color{#d91a1a}-0.99\%$
test_step_mdp_speed[False-True-True-False-True] 41.9780μs 15.9150μs 62.8339 KOps/s 63.1679 KOps/s $\color{#d91a1a}-0.53\%$
test_step_mdp_speed[False-True-True-False-False] 28.4430μs 10.0568μs 99.4353 KOps/s 100.2813 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[False-True-False-True-True] 39.2130μs 25.7082μs 38.8981 KOps/s 39.4737 KOps/s $\color{#d91a1a}-1.46\%$
test_step_mdp_speed[False-True-False-True-False] 43.7520μs 16.7664μs 59.6431 KOps/s 60.2523 KOps/s $\color{#d91a1a}-1.01\%$
test_step_mdp_speed[False-True-False-False-True] 44.2220μs 17.1894μs 58.1753 KOps/s 58.8727 KOps/s $\color{#d91a1a}-1.18\%$
test_step_mdp_speed[False-True-False-False-False] 32.9210μs 11.3475μs 88.1252 KOps/s 90.1712 KOps/s $\color{#d91a1a}-2.27\%$
test_step_mdp_speed[False-False-True-True-True] 63.7590μs 26.6975μs 37.4567 KOps/s 38.1418 KOps/s $\color{#d91a1a}-1.80\%$
test_step_mdp_speed[False-False-True-True-False] 41.4670μs 18.2679μs 54.7409 KOps/s 55.8084 KOps/s $\color{#d91a1a}-1.91\%$
test_step_mdp_speed[False-False-True-False-True] 42.0080μs 17.2814μs 57.8656 KOps/s 59.2865 KOps/s $\color{#d91a1a}-2.40\%$
test_step_mdp_speed[False-False-True-False-False] 32.6310μs 11.3837μs 87.8445 KOps/s 90.0846 KOps/s $\color{#d91a1a}-2.49\%$
test_step_mdp_speed[False-False-False-True-True] 52.2080μs 27.5231μs 36.3331 KOps/s 36.7013 KOps/s $\color{#d91a1a}-1.00\%$
test_step_mdp_speed[False-False-False-True-False] 66.1530μs 19.1665μs 52.1743 KOps/s 53.0692 KOps/s $\color{#d91a1a}-1.69\%$
test_step_mdp_speed[False-False-False-False-True] 61.5640μs 18.0317μs 55.4580 KOps/s 56.1261 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[False-False-False-False-False] 67.4260μs 12.1525μs 82.2879 KOps/s 81.5930 KOps/s $\color{#35bf28}+0.85\%$
test_values[generalized_advantage_estimate-True-True] 9.6037ms 9.2810ms 107.7468 Ops/s 108.9012 Ops/s $\color{#d91a1a}-1.06\%$
test_values[vec_generalized_advantage_estimate-True-True] 34.9365ms 33.2084ms 30.1128 Ops/s 28.5314 Ops/s $\textbf{\color{#35bf28}+5.54\%}$
test_values[td0_return_estimate-False-False] 0.2256ms 0.1674ms 5.9737 KOps/s 6.0447 KOps/s $\color{#d91a1a}-1.18\%$
test_values[td1_return_estimate-False-False] 25.8353ms 22.9441ms 43.5841 Ops/s 43.8748 Ops/s $\color{#d91a1a}-0.66\%$
test_values[vec_td1_return_estimate-False-False] 34.7455ms 33.4275ms 29.9155 Ops/s 28.4051 Ops/s $\textbf{\color{#35bf28}+5.32\%}$
test_values[td_lambda_return_estimate-True-False] 33.9539ms 33.2580ms 30.0679 Ops/s 30.6869 Ops/s $\color{#d91a1a}-2.02\%$
test_values[vec_td_lambda_return_estimate-True-False] 48.8099ms 33.7476ms 29.6318 Ops/s 28.4440 Ops/s $\color{#35bf28}+4.18\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.1742ms 8.0638ms 124.0116 Ops/s 122.7767 Ops/s $\color{#35bf28}+1.01\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4900ms 1.9832ms 504.2327 Ops/s 517.6443 Ops/s $\color{#d91a1a}-2.59\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5083ms 0.3498ms 2.8588 KOps/s 2.8735 KOps/s $\color{#d91a1a}-0.51\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 47.1793ms 45.8074ms 21.8306 Ops/s 24.3231 Ops/s $\textbf{\color{#d91a1a}-10.25\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.7008ms 3.0301ms 330.0259 Ops/s 331.0071 Ops/s $\color{#d91a1a}-0.30\%$
test_dqn_speed 7.0746ms 1.3104ms 763.1171 Ops/s 702.1776 Ops/s $\textbf{\color{#35bf28}+8.68\%}$
test_ddpg_speed 3.2964ms 2.6206ms 381.5862 Ops/s 381.9416 Ops/s $\color{#d91a1a}-0.09\%$
test_sac_speed 8.6062ms 8.0819ms 123.7337 Ops/s 124.5231 Ops/s $\color{#d91a1a}-0.63\%$
test_redq_speed 14.4032ms 12.9146ms 77.4316 Ops/s 76.9223 Ops/s $\color{#35bf28}+0.66\%$
test_redq_deprec_speed 14.5060ms 12.9529ms 77.2026 Ops/s 78.0139 Ops/s $\color{#d91a1a}-1.04\%$
test_td3_speed 15.6323ms 8.0698ms 123.9182 Ops/s 126.2167 Ops/s $\color{#d91a1a}-1.82\%$
test_cql_speed 37.1962ms 36.0593ms 27.7321 Ops/s 27.9731 Ops/s $\color{#d91a1a}-0.86\%$
test_a2c_speed 8.4992ms 7.3819ms 135.4672 Ops/s 137.2046 Ops/s $\color{#d91a1a}-1.27\%$
test_ppo_speed 8.1392ms 7.6703ms 130.3724 Ops/s 130.2123 Ops/s $\color{#35bf28}+0.12\%$
test_reinforce_speed 8.2138ms 6.6238ms 150.9698 Ops/s 153.9077 Ops/s $\color{#d91a1a}-1.91\%$
test_iql_speed 33.6336ms 32.4761ms 30.7918 Ops/s 30.9674 Ops/s $\color{#d91a1a}-0.57\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.3097ms 2.1726ms 460.2818 Ops/s 463.0710 Ops/s $\color{#d91a1a}-0.60\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9766ms 0.5085ms 1.9664 KOps/s 2.0231 KOps/s $\color{#d91a1a}-2.80\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7654ms 0.4715ms 2.1211 KOps/s 2.1352 KOps/s $\color{#d91a1a}-0.66\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.4993ms 2.2103ms 452.4304 Ops/s 449.7914 Ops/s $\color{#35bf28}+0.59\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0303ms 0.4885ms 2.0471 KOps/s 2.0580 KOps/s $\color{#d91a1a}-0.53\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7619ms 0.4624ms 2.1625 KOps/s 2.1528 KOps/s $\color{#35bf28}+0.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6513ms 1.2069ms 828.5474 Ops/s 815.3576 Ops/s $\color{#35bf28}+1.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6807ms 1.1423ms 875.4139 Ops/s 882.4491 Ops/s $\color{#d91a1a}-0.80\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4009ms 2.2430ms 445.8377 Ops/s 440.2813 Ops/s $\color{#35bf28}+1.26\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 94.2201ms 0.6817ms 1.4668 KOps/s 1.6287 KOps/s $\textbf{\color{#d91a1a}-9.94\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9143ms 0.5801ms 1.7237 KOps/s 1.7314 KOps/s $\color{#d91a1a}-0.45\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.3484ms 2.1429ms 466.6634 Ops/s 468.3815 Ops/s $\color{#d91a1a}-0.37\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0560ms 0.5027ms 1.9891 KOps/s 2.0121 KOps/s $\color{#d91a1a}-1.14\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7607ms 0.4688ms 2.1329 KOps/s 2.0785 KOps/s $\color{#35bf28}+2.62\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.3423ms 2.1956ms 455.4480 Ops/s 458.6440 Ops/s $\color{#d91a1a}-0.70\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.5993ms 0.4954ms 2.0185 KOps/s 2.0529 KOps/s $\color{#d91a1a}-1.68\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.8267ms 0.4711ms 2.1226 KOps/s 2.1399 KOps/s $\color{#d91a1a}-0.81\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4426ms 2.2533ms 443.7874 Ops/s 431.1236 Ops/s $\color{#35bf28}+2.94\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8115ms 0.6096ms 1.6404 KOps/s 1.6371 KOps/s $\color{#35bf28}+0.20\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9044ms 0.5928ms 1.6870 KOps/s 1.7011 KOps/s $\color{#d91a1a}-0.83\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1075s 7.5735ms 132.0398 Ops/s 134.5307 Ops/s $\color{#d91a1a}-1.85\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.4532ms 11.9930ms 83.3822 Ops/s 81.8069 Ops/s $\color{#35bf28}+1.93\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.7895ms 1.0678ms 936.5387 Ops/s 929.7072 Ops/s $\color{#35bf28}+0.73\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 94.7671ms 5.4680ms 182.8838 Ops/s 174.7849 Ops/s $\color{#35bf28}+4.63\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.4019ms 11.9908ms 83.3974 Ops/s 70.8290 Ops/s $\textbf{\color{#35bf28}+17.74\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.5344ms 1.0184ms 981.8988 Ops/s 883.0095 Ops/s $\textbf{\color{#35bf28}+11.20\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 87.8470ms 5.6087ms 178.2939 Ops/s 165.2859 Ops/s $\textbf{\color{#35bf28}+7.87\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1078s 14.2940ms 69.9594 Ops/s 81.1863 Ops/s $\textbf{\color{#d91a1a}-13.83\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.4443ms 1.4197ms 704.3558 Ops/s 694.1492 Ops/s $\color{#35bf28}+1.47\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 23, 2024 •
edited
Loading

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of GPU Benchmark Tests

Total Benchmarks: 94. Improved: $\large\color{#35bf28}2$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1035s 0.1033s 9.6772 Ops/s 9.3151 Ops/s $\color{#35bf28}+3.89\%$
test_sync 93.0818ms 88.9962ms 11.2364 Ops/s 11.2809 Ops/s $\color{#d91a1a}-0.39\%$
test_async 0.1746s 88.2116ms 11.3364 Ops/s 11.2854 Ops/s $\color{#35bf28}+0.45\%$
test_single_pixels 0.1134s 0.1121s 8.9184 Ops/s 9.0496 Ops/s $\color{#d91a1a}-1.45\%$
test_sync_pixels 69.2459ms 67.1083ms 14.9013 Ops/s 14.9503 Ops/s $\color{#d91a1a}-0.33\%$
test_async_pixels 0.1181s 57.6215ms 17.3546 Ops/s 17.5991 Ops/s $\color{#d91a1a}-1.39\%$
test_simple 0.7576s 0.6793s 1.4720 Ops/s 1.5072 Ops/s $\color{#d91a1a}-2.33\%$
test_transformed 0.9460s 0.8835s 1.1318 Ops/s 1.1782 Ops/s $\color{#d91a1a}-3.94\%$
test_serial 2.1657s 2.0781s 0.4812 Ops/s 0.4858 Ops/s $\color{#d91a1a}-0.94\%$
test_parallel 1.9342s 1.8720s 0.5342 Ops/s 0.5422 Ops/s $\color{#d91a1a}-1.47\%$
test_step_mdp_speed[True-True-True-True-True] 79.0710μs 34.0120μs 29.4014 KOps/s 30.2195 KOps/s $\color{#d91a1a}-2.71\%$
test_step_mdp_speed[True-True-True-True-False] 44.5600μs 19.9878μs 50.0304 KOps/s 51.4222 KOps/s $\color{#d91a1a}-2.71\%$
test_step_mdp_speed[True-True-True-False-True] 45.7610μs 18.9264μs 52.8363 KOps/s 53.5793 KOps/s $\color{#d91a1a}-1.39\%$
test_step_mdp_speed[True-True-True-False-False] 35.5500μs 11.3354μs 88.2194 KOps/s 89.9330 KOps/s $\color{#d91a1a}-1.91\%$
test_step_mdp_speed[True-True-False-True-True] 59.6510μs 35.1060μs 28.4852 KOps/s 28.8296 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[True-True-False-True-False] 42.9000μs 21.6440μs 46.2021 KOps/s 47.2582 KOps/s $\color{#d91a1a}-2.23\%$
test_step_mdp_speed[True-True-False-False-True] 45.4100μs 20.9775μs 47.6701 KOps/s 48.8899 KOps/s $\color{#d91a1a}-2.49\%$
test_step_mdp_speed[True-True-False-False-False] 38.0700μs 13.1368μs 76.1221 KOps/s 77.1854 KOps/s $\color{#d91a1a}-1.38\%$
test_step_mdp_speed[True-False-True-True-True] 55.6720μs 37.0439μs 26.9950 KOps/s 27.3912 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[True-False-True-True-False] 45.8910μs 23.5181μs 42.5205 KOps/s 43.3728 KOps/s $\color{#d91a1a}-1.97\%$
test_step_mdp_speed[True-False-True-False-True] 45.4410μs 20.7553μs 48.1804 KOps/s 48.8799 KOps/s $\color{#d91a1a}-1.43\%$
test_step_mdp_speed[True-False-True-False-False] 29.2210μs 13.1701μs 75.9298 KOps/s 76.9768 KOps/s $\color{#d91a1a}-1.36\%$
test_step_mdp_speed[True-False-False-True-True] 67.0410μs 39.2291μs 25.4913 KOps/s 26.3559 KOps/s $\color{#d91a1a}-3.28\%$
test_step_mdp_speed[True-False-False-True-False] 50.4810μs 25.5870μs 39.0824 KOps/s 39.5394 KOps/s $\color{#d91a1a}-1.16\%$
test_step_mdp_speed[True-False-False-False-True] 39.9510μs 22.7304μs 43.9940 KOps/s 44.8202 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[True-False-False-False-False] 37.9800μs 14.9800μs 66.7556 KOps/s 67.0492 KOps/s $\color{#d91a1a}-0.44\%$
test_step_mdp_speed[False-True-True-True-True] 62.5310μs 37.2534μs 26.8432 KOps/s 27.1266 KOps/s $\color{#d91a1a}-1.04\%$
test_step_mdp_speed[False-True-True-True-False] 45.4500μs 23.5169μs 42.5226 KOps/s 43.2176 KOps/s $\color{#d91a1a}-1.61\%$
test_step_mdp_speed[False-True-True-False-True] 63.1510μs 24.8143μs 40.2993 KOps/s 40.5782 KOps/s $\color{#d91a1a}-0.69\%$
test_step_mdp_speed[False-True-True-False-False] 37.3810μs 15.1288μs 66.0992 KOps/s 66.9026 KOps/s $\color{#d91a1a}-1.20\%$
test_step_mdp_speed[False-True-False-True-True] 63.1510μs 39.2050μs 25.5070 KOps/s 25.7396 KOps/s $\color{#d91a1a}-0.90\%$
test_step_mdp_speed[False-True-False-True-False] 61.0220μs 25.6408μs 39.0004 KOps/s 39.4072 KOps/s $\color{#d91a1a}-1.03\%$
test_step_mdp_speed[False-True-False-False-True] 48.3510μs 26.6417μs 37.5351 KOps/s 37.6823 KOps/s $\color{#d91a1a}-0.39\%$
test_step_mdp_speed[False-True-False-False-False] 39.9000μs 16.8884μs 59.2124 KOps/s 59.9314 KOps/s $\color{#d91a1a}-1.20\%$
test_step_mdp_speed[False-False-True-True-True] 65.5020μs 40.7614μs 24.5330 KOps/s 24.8924 KOps/s $\color{#d91a1a}-1.44\%$
test_step_mdp_speed[False-False-True-True-False] 52.0810μs 27.4270μs 36.4604 KOps/s 36.9657 KOps/s $\color{#d91a1a}-1.37\%$
test_step_mdp_speed[False-False-True-False-True] 49.5010μs 26.6181μs 37.5684 KOps/s 38.0665 KOps/s $\color{#d91a1a}-1.31\%$
test_step_mdp_speed[False-False-True-False-False] 41.2910μs 17.0061μs 58.8023 KOps/s 60.1235 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[False-False-False-True-True] 59.4610μs 42.0526μs 23.7797 KOps/s 23.9034 KOps/s $\color{#d91a1a}-0.52\%$
test_step_mdp_speed[False-False-False-True-False] 51.6010μs 29.1575μs 34.2965 KOps/s 34.6717 KOps/s $\color{#d91a1a}-1.08\%$
test_step_mdp_speed[False-False-False-False-True] 50.9910μs 28.1918μs 35.4714 KOps/s 36.0008 KOps/s $\color{#d91a1a}-1.47\%$
test_step_mdp_speed[False-False-False-False-False] 40.4510μs 18.6121μs 53.7286 KOps/s 54.4699 KOps/s $\color{#d91a1a}-1.36\%$
test_values[generalized_advantage_estimate-True-True] 23.8586ms 23.4132ms 42.7110 Ops/s 43.4490 Ops/s $\color{#d91a1a}-1.70\%$
test_values[vec_generalized_advantage_estimate-True-True] 84.7250ms 3.2575ms 306.9883 Ops/s 314.3966 Ops/s $\color{#d91a1a}-2.36\%$
test_values[td0_return_estimate-False-False] 93.3010μs 62.9863μs 15.8765 KOps/s 15.9161 KOps/s $\color{#d91a1a}-0.25\%$
test_values[td1_return_estimate-False-False] 52.9034ms 52.7069ms 18.9729 Ops/s 19.3013 Ops/s $\color{#d91a1a}-1.70\%$
test_values[vec_td1_return_estimate-False-False] 1.9835ms 1.7560ms 569.4793 Ops/s 570.7132 Ops/s $\color{#d91a1a}-0.22\%$
test_values[td_lambda_return_estimate-True-False] 83.8469ms 83.4685ms 11.9806 Ops/s 12.0082 Ops/s $\color{#d91a1a}-0.23\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.0516ms 1.7545ms 569.9621 Ops/s 571.7222 Ops/s $\color{#d91a1a}-0.31\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.0008ms 22.8031ms 43.8537 Ops/s 44.1552 Ops/s $\color{#d91a1a}-0.68\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8742ms 0.6962ms 1.4363 KOps/s 1.4516 KOps/s $\color{#d91a1a}-1.05\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7174ms 0.6443ms 1.5521 KOps/s 1.5611 KOps/s $\color{#d91a1a}-0.58\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.4950ms 1.4499ms 689.7231 Ops/s 693.5621 Ops/s $\color{#d91a1a}-0.55\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9310ms 0.6618ms 1.5110 KOps/s 1.5141 KOps/s $\color{#d91a1a}-0.21\%$
test_dqn_speed 1.7540ms 1.4475ms 690.8665 Ops/s 697.4529 Ops/s $\color{#d91a1a}-0.94\%$
test_ddpg_speed 3.3106ms 2.7261ms 366.8195 Ops/s 368.5169 Ops/s $\color{#d91a1a}-0.46\%$
test_sac_speed 8.4987ms 8.0034ms 124.9463 Ops/s 126.3131 Ops/s $\color{#d91a1a}-1.08\%$
test_redq_speed 10.9344ms 10.1483ms 98.5383 Ops/s 98.9360 Ops/s $\color{#d91a1a}-0.40\%$
test_redq_deprec_speed 11.3637ms 10.6240ms 94.1264 Ops/s 90.6965 Ops/s $\color{#35bf28}+3.78\%$
test_td3_speed 7.9875ms 7.9252ms 126.1806 Ops/s 124.1389 Ops/s $\color{#35bf28}+1.64\%$
test_cql_speed 25.4105ms 24.7822ms 40.3516 Ops/s 40.7451 Ops/s $\color{#d91a1a}-0.97\%$
test_a2c_speed 5.6825ms 5.4327ms 184.0700 Ops/s 182.8853 Ops/s $\color{#35bf28}+0.65\%$
test_ppo_speed 6.0807ms 5.8180ms 171.8810 Ops/s 170.5396 Ops/s $\color{#35bf28}+0.79\%$
test_reinforce_speed 4.7441ms 4.4158ms 226.4617 Ops/s 227.4175 Ops/s $\color{#d91a1a}-0.42\%$
test_iql_speed 19.6599ms 19.0180ms 52.5818 Ops/s 53.1518 Ops/s $\color{#d91a1a}-1.07\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.9684ms 2.8807ms 347.1331 Ops/s 343.2078 Ops/s $\color{#35bf28}+1.14\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0346ms 0.5356ms 1.8671 KOps/s 1.8768 KOps/s $\color{#d91a1a}-0.52\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7011ms 0.5132ms 1.9487 KOps/s 1.9504 KOps/s $\color{#d91a1a}-0.09\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.0868ms 2.9000ms 344.8264 Ops/s 343.4632 Ops/s $\color{#35bf28}+0.40\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2552ms 0.5298ms 1.8875 KOps/s 1.9089 KOps/s $\color{#d91a1a}-1.12\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6448ms 0.5046ms 1.9818 KOps/s 1.9841 KOps/s $\color{#d91a1a}-0.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 3.7205ms 1.4318ms 698.4448 Ops/s 706.4487 Ops/s $\color{#d91a1a}-1.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5978ms 1.3843ms 722.3853 Ops/s 746.2674 Ops/s $\color{#d91a1a}-3.20\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1147ms 3.0056ms 332.7162 Ops/s 332.5683 Ops/s $\color{#35bf28}+0.04\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8443ms 0.6576ms 1.5206 KOps/s 1.3282 KOps/s $\textbf{\color{#35bf28}+14.49\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8268ms 0.6315ms 1.5835 KOps/s 1.5673 KOps/s $\color{#35bf28}+1.03\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0750ms 2.8432ms 351.7127 Ops/s 341.9600 Ops/s $\color{#35bf28}+2.85\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6374ms 0.5374ms 1.8608 KOps/s 1.8664 KOps/s $\color{#d91a1a}-0.30\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6433ms 0.5123ms 1.9521 KOps/s 1.9440 KOps/s $\color{#35bf28}+0.42\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9890ms 2.8708ms 348.3327 Ops/s 343.5589 Ops/s $\color{#35bf28}+1.39\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6895ms 0.5293ms 1.8893 KOps/s 1.8870 KOps/s $\color{#35bf28}+0.12\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5969ms 0.5041ms 1.9838 KOps/s 1.9493 KOps/s $\color{#35bf28}+1.77\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1215ms 3.0016ms 333.1509 Ops/s 327.5977 Ops/s $\color{#35bf28}+1.70\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8294ms 0.6617ms 1.5114 KOps/s 1.5140 KOps/s $\color{#d91a1a}-0.17\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7898ms 0.6349ms 1.5750 KOps/s 1.5706 KOps/s $\color{#35bf28}+0.28\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1234s 9.4815ms 105.4685 Ops/s 132.7344 Ops/s $\textbf{\color{#d91a1a}-20.54\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 18.8486ms 14.8919ms 67.1507 Ops/s 66.7304 Ops/s $\color{#35bf28}+0.63\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.1195ms 1.0387ms 962.7805 Ops/s 964.0952 Ops/s $\color{#d91a1a}-0.14\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1158s 7.0987ms 140.8711 Ops/s 106.7808 Ops/s $\textbf{\color{#35bf28}+31.93\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.3520ms 14.9940ms 66.6931 Ops/s 66.5359 Ops/s $\color{#35bf28}+0.24\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.3225ms 1.1673ms 856.6759 Ops/s 954.8624 Ops/s $\textbf{\color{#d91a1a}-10.28\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1193s 9.7349ms 102.7235 Ops/s 133.6155 Ops/s $\textbf{\color{#d91a1a}-23.12\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.3436ms 15.2303ms 65.6588 Ops/s 65.1250 Ops/s $\color{#35bf28}+0.82\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.2538ms 1.6123ms 620.2244 Ops/s 675.8437 Ops/s $\textbf{\color{#d91a1a}-8.23\%}$

@vmoens vmoens merged commit e835770 into main Mar 24, 2024
66 of 67 checks passed
vmoens added a commit that referenced this pull request Mar 25, 2024
@vmoens
[BugFix] Fix strict_length=True in SliceSampler (#2037)
4cf0655 
(cherry picked from commit e835770)
@vmoens vmoens deleted the fix-strictlength branch April 3, 2024 06:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@vmoens @facebook-github-bot