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

[Doc] Better doc for inverse transform semantic #2459

Merged
merged 4 commits into from
Sep 30, 2024
Merged

[Doc] Better doc for inverse transform semantic #2459

merged 4 commits into from
Sep 30, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Sep 30, 2024 •
edited
Loading

@vmoens
Update
679a3ae 
[ghstack-poisoned]
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Sep 30, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2459

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 18 New Failures, 4 Unrelated Failures

As of commit 07c7eef with merge base a0dfddc (image):

NEW FAILURES - The following jobs have failed:

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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

vmoens added a commit that referenced this pull request Sep 30, 2024
@vmoens
[Doc] Better doc for inverse transform semantic
37a727f 
ghstack-source-id: 444ad87d1ab0a829e8ce1848b5838859d5ee7494
Pull Request resolved: #2459
@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 Sep 30, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Sep 30, 2024 •
edited
Loading

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

Total Benchmarks: 146. Improved: $\large\color{#35bf28}25$. Worsened: $\large\color{#d91a1a}7$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 64.4972ms 62.2544ms 16.0631 Ops/s 15.9598 Ops/s $\color{#35bf28}+0.65\%$
test_sync 40.4307ms 33.8133ms 29.5741 Ops/s 27.6866 Ops/s $\textbf{\color{#35bf28}+6.82\%}$
test_async 0.1063s 32.4396ms 30.8265 Ops/s 30.4626 Ops/s $\color{#35bf28}+1.19\%$
test_simple 0.5479s 0.4503s 2.2208 Ops/s 2.3468 Ops/s $\textbf{\color{#d91a1a}-5.37\%}$
test_transformed 0.7046s 0.6199s 1.6132 Ops/s 1.6577 Ops/s $\color{#d91a1a}-2.69\%$
test_serial 1.4201s 1.3249s 0.7548 Ops/s 0.7450 Ops/s $\color{#35bf28}+1.31\%$
test_parallel 1.2685s 1.1679s 0.8562 Ops/s 0.8608 Ops/s $\color{#d91a1a}-0.53\%$
test_step_mdp_speed[True-True-True-True-True] 0.2953ms 27.8193μs 35.9462 KOps/s 36.3068 KOps/s $\color{#d91a1a}-0.99\%$
test_step_mdp_speed[True-True-True-True-False] 74.6300μs 16.2554μs 61.5182 KOps/s 61.9241 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-True-True-False-True] 54.3420μs 15.8747μs 62.9935 KOps/s 63.4963 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-True-True-False-False] 55.4740μs 9.3656μs 106.7734 KOps/s 107.3748 KOps/s $\color{#d91a1a}-0.56\%$
test_step_mdp_speed[True-True-False-True-True] 97.4830μs 29.4274μs 33.9819 KOps/s 34.0789 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[True-True-False-True-False] 74.1590μs 18.0554μs 55.3852 KOps/s 56.8803 KOps/s $\color{#d91a1a}-2.63\%$
test_step_mdp_speed[True-True-False-False-True] 46.5280μs 17.6315μs 56.7167 KOps/s 57.2976 KOps/s $\color{#d91a1a}-1.01\%$
test_step_mdp_speed[True-True-False-False-False] 60.2130μs 10.8594μs 92.0862 KOps/s 91.1371 KOps/s $\color{#35bf28}+1.04\%$
test_step_mdp_speed[True-False-True-True-True] 87.3440μs 31.8374μs 31.4096 KOps/s 31.8461 KOps/s $\color{#d91a1a}-1.37\%$
test_step_mdp_speed[True-False-True-True-False] 53.7310μs 19.9121μs 50.2208 KOps/s 51.3486 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[True-False-True-False-True] 63.4990μs 17.5203μs 57.0766 KOps/s 57.5624 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[True-False-True-False-False] 40.6970μs 10.8840μs 91.8781 KOps/s 91.6076 KOps/s $\color{#35bf28}+0.30\%$
test_step_mdp_speed[True-False-False-True-True] 86.7950μs 32.6450μs 30.6325 KOps/s 30.4291 KOps/s $\color{#35bf28}+0.67\%$
test_step_mdp_speed[True-False-False-True-False] 52.0480μs 21.1223μs 47.3434 KOps/s 47.6594 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-False-False-False-True] 54.3320μs 19.2364μs 51.9846 KOps/s 53.0013 KOps/s $\color{#d91a1a}-1.92\%$
test_step_mdp_speed[True-False-False-False-False] 42.4100μs 12.6548μs 79.0217 KOps/s 79.8608 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[False-True-True-True-True] 79.2580μs 31.5669μs 31.6787 KOps/s 32.2700 KOps/s $\color{#d91a1a}-1.83\%$
test_step_mdp_speed[False-True-True-True-False] 53.2900μs 19.7645μs 50.5957 KOps/s 51.4733 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[False-True-True-False-True] 62.5280μs 20.8620μs 47.9341 KOps/s 50.6144 KOps/s $\textbf{\color{#d91a1a}-5.30\%}$
test_step_mdp_speed[False-True-True-False-False] 47.3490μs 12.3740μs 80.8144 KOps/s 82.2583 KOps/s $\color{#d91a1a}-1.76\%$
test_step_mdp_speed[False-True-False-True-True] 83.9980μs 33.0899μs 30.2207 KOps/s 30.5983 KOps/s $\color{#d91a1a}-1.23\%$
test_step_mdp_speed[False-True-False-True-False] 60.1820μs 21.2682μs 47.0185 KOps/s 47.8454 KOps/s $\color{#d91a1a}-1.73\%$
test_step_mdp_speed[False-True-False-False-True] 3.0177ms 22.0675μs 45.3156 KOps/s 45.2095 KOps/s $\color{#35bf28}+0.23\%$
test_step_mdp_speed[False-True-False-False-False] 56.0550μs 13.8276μs 72.3191 KOps/s 73.1758 KOps/s $\color{#d91a1a}-1.17\%$
test_step_mdp_speed[False-False-True-True-True] 87.0540μs 34.7696μs 28.7608 KOps/s 29.1306 KOps/s $\color{#d91a1a}-1.27\%$
test_step_mdp_speed[False-False-True-True-False] 61.6260μs 23.1163μs 43.2595 KOps/s 44.3212 KOps/s $\color{#d91a1a}-2.40\%$
test_step_mdp_speed[False-False-True-False-True] 86.4190μs 22.3675μs 44.7077 KOps/s 46.1068 KOps/s $\color{#d91a1a}-3.03\%$
test_step_mdp_speed[False-False-True-False-False] 62.7980μs 13.8874μs 72.0076 KOps/s 73.6970 KOps/s $\color{#d91a1a}-2.29\%$
test_step_mdp_speed[False-False-False-True-True] 91.3710μs 36.2592μs 27.5792 KOps/s 28.2849 KOps/s $\color{#d91a1a}-2.49\%$
test_step_mdp_speed[False-False-False-True-False] 68.9090μs 24.4813μs 40.8474 KOps/s 42.2477 KOps/s $\color{#d91a1a}-3.31\%$
test_step_mdp_speed[False-False-False-False-True] 71.4740μs 23.1748μs 43.1504 KOps/s 43.9500 KOps/s $\color{#d91a1a}-1.82\%$
test_step_mdp_speed[False-False-False-False-False] 48.0000μs 15.3963μs 64.9507 KOps/s 65.9021 KOps/s $\color{#d91a1a}-1.44\%$
test_values[generalized_advantage_estimate-True-True] 10.5280ms 10.0093ms 99.9066 Ops/s 102.4008 Ops/s $\color{#d91a1a}-2.44\%$
test_values[vec_generalized_advantage_estimate-True-True] 38.5312ms 36.7277ms 27.2274 Ops/s 29.0835 Ops/s $\textbf{\color{#d91a1a}-6.38\%}$
test_values[td0_return_estimate-False-False] 0.3073ms 0.1872ms 5.3420 KOps/s 4.9363 KOps/s $\textbf{\color{#35bf28}+8.22\%}$
test_values[td1_return_estimate-False-False] 28.7387ms 24.9475ms 40.0842 Ops/s 41.1709 Ops/s $\color{#d91a1a}-2.64\%$
test_values[vec_td1_return_estimate-False-False] 38.3105ms 36.8745ms 27.1190 Ops/s 28.5202 Ops/s $\color{#d91a1a}-4.91\%$
test_values[td_lambda_return_estimate-True-False] 39.4693ms 35.7649ms 27.9604 Ops/s 28.4672 Ops/s $\color{#d91a1a}-1.78\%$
test_values[vec_td_lambda_return_estimate-True-False] 39.4814ms 36.8276ms 27.1535 Ops/s 28.8460 Ops/s $\textbf{\color{#d91a1a}-5.87\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 12.6477ms 8.5113ms 117.4909 Ops/s 120.0387 Ops/s $\color{#d91a1a}-2.12\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4969ms 2.0020ms 499.5012 Ops/s 497.3892 Ops/s $\color{#35bf28}+0.42\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6146ms 0.3649ms 2.7406 KOps/s 2.7406 KOps/s $-0.00\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 50.8487ms 49.6982ms 20.1214 Ops/s 23.2610 Ops/s $\textbf{\color{#d91a1a}-13.50\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8842ms 3.0862ms 324.0265 Ops/s 324.0842 Ops/s $\color{#d91a1a}-0.02\%$
test_dqn_speed[False-None] 7.1756ms 1.3863ms 721.3463 Ops/s 734.4503 Ops/s $\color{#d91a1a}-1.78\%$
test_dqn_speed[False-backward] 2.0633ms 1.8946ms 527.8095 Ops/s 534.0037 Ops/s $\color{#d91a1a}-1.16\%$
test_dqn_speed[True-None] 1.2992ms 0.4691ms 2.1317 KOps/s 2.1266 KOps/s $\color{#35bf28}+0.24\%$
test_dqn_speed[True-backward] 1.0598ms 0.9292ms 1.0762 KOps/s 1.0102 KOps/s $\textbf{\color{#35bf28}+6.54\%}$
test_dqn_speed[reduce-overhead-None] 0.8101ms 0.4784ms 2.0902 KOps/s 2.1428 KOps/s $\color{#d91a1a}-2.45\%$
test_dqn_speed[reduce-overhead-backward] 1.0494ms 0.9149ms 1.0930 KOps/s 1.0948 KOps/s $\color{#d91a1a}-0.16\%$
test_ddpg_speed[False-None] 3.7550ms 2.8777ms 347.5051 Ops/s 352.7507 Ops/s $\color{#d91a1a}-1.49\%$
test_ddpg_speed[False-backward] 5.0313ms 4.1058ms 243.5608 Ops/s 248.2900 Ops/s $\color{#d91a1a}-1.90\%$
test_ddpg_speed[True-None] 1.4312ms 1.0245ms 976.0468 Ops/s 975.2901 Ops/s $\color{#35bf28}+0.08\%$
test_ddpg_speed[True-backward] 2.0068ms 1.9142ms 522.4176 Ops/s 511.1758 Ops/s $\color{#35bf28}+2.20\%$
test_ddpg_speed[reduce-overhead-None] 1.5014ms 1.0147ms 985.4937 Ops/s 986.4522 Ops/s $\color{#d91a1a}-0.10\%$
test_ddpg_speed[reduce-overhead-backward] 2.2765ms 1.9586ms 510.5763 Ops/s 507.1322 Ops/s $\color{#35bf28}+0.68\%$
test_sac_speed[False-None] 10.2049ms 8.7491ms 114.2977 Ops/s 117.3568 Ops/s $\color{#d91a1a}-2.61\%$
test_sac_speed[False-backward] 13.3379ms 12.1249ms 82.4749 Ops/s 86.2669 Ops/s $\color{#d91a1a}-4.40\%$
test_sac_speed[True-None] 3.6283ms 1.9030ms 525.4794 Ops/s 513.6146 Ops/s $\color{#35bf28}+2.31\%$
test_sac_speed[True-backward] 4.3739ms 3.8965ms 256.6432 Ops/s 255.6733 Ops/s $\color{#35bf28}+0.38\%$
test_sac_speed[reduce-overhead-None] 2.4311ms 1.9101ms 523.5421 Ops/s 512.0873 Ops/s $\color{#35bf28}+2.24\%$
test_sac_speed[reduce-overhead-backward] 4.4839ms 3.8535ms 259.5016 Ops/s 263.7704 Ops/s $\color{#d91a1a}-1.62\%$
test_redq_speed[False-None] 20.5181ms 14.1351ms 70.7459 Ops/s 68.2687 Ops/s $\color{#35bf28}+3.63\%$
test_redq_speed[False-backward] 26.3986ms 24.1783ms 41.3593 Ops/s 41.8727 Ops/s $\color{#d91a1a}-1.23\%$
test_redq_speed[True-None] 6.6390ms 5.6892ms 175.7727 Ops/s 175.7838 Ops/s $-0.01\%$
test_redq_speed[True-backward] 15.7885ms 13.6103ms 73.4735 Ops/s 71.8916 Ops/s $\color{#35bf28}+2.20\%$
test_redq_speed[reduce-overhead-None] 6.6291ms 5.6190ms 177.9681 Ops/s 165.4312 Ops/s $\textbf{\color{#35bf28}+7.58\%}$
test_redq_speed[reduce-overhead-backward] 14.0164ms 13.3345ms 74.9937 Ops/s 72.8061 Ops/s $\color{#35bf28}+3.00\%$
test_redq_deprec_speed[False-None] 16.2812ms 13.9019ms 71.9327 Ops/s 70.5012 Ops/s $\color{#35bf28}+2.03\%$
test_redq_deprec_speed[False-backward] 22.4506ms 20.4291ms 48.9498 Ops/s 48.1626 Ops/s $\color{#35bf28}+1.63\%$
test_redq_deprec_speed[True-None] 5.4683ms 4.0491ms 246.9682 Ops/s 243.7468 Ops/s $\color{#35bf28}+1.32\%$
test_redq_deprec_speed[True-backward] 10.1661ms 8.9129ms 112.1970 Ops/s 107.2677 Ops/s $\color{#35bf28}+4.60\%$
test_redq_deprec_speed[reduce-overhead-None] 5.2353ms 4.3204ms 231.4626 Ops/s 237.6434 Ops/s $\color{#d91a1a}-2.60\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.9482ms 9.2099ms 108.5794 Ops/s 106.0087 Ops/s $\color{#35bf28}+2.42\%$
test_td3_speed[False-None] 43.2231ms 8.6292ms 115.8858 Ops/s 115.9280 Ops/s $\color{#d91a1a}-0.04\%$
test_td3_speed[False-backward] 13.2056ms 11.6083ms 86.1454 Ops/s 87.2698 Ops/s $\color{#d91a1a}-1.29\%$
test_td3_speed[True-None] 2.3479ms 1.9837ms 504.1181 Ops/s 470.9188 Ops/s $\textbf{\color{#35bf28}+7.05\%}$
test_td3_speed[True-backward] 4.7076ms 3.8850ms 257.4027 Ops/s 239.8862 Ops/s $\textbf{\color{#35bf28}+7.30\%}$
test_td3_speed[reduce-overhead-None] 2.4736ms 2.0028ms 499.3056 Ops/s 475.1340 Ops/s $\textbf{\color{#35bf28}+5.09\%}$
test_td3_speed[reduce-overhead-backward] 4.5908ms 3.7765ms 264.7938 Ops/s 255.5905 Ops/s $\color{#35bf28}+3.60\%$
test_cql_speed[False-None] 38.3837ms 36.1800ms 27.6395 Ops/s 26.4988 Ops/s $\color{#35bf28}+4.30\%$
test_cql_speed[False-backward] 59.8338ms 47.7616ms 20.9373 Ops/s 20.6498 Ops/s $\color{#35bf28}+1.39\%$
test_cql_speed[True-None] 17.2727ms 16.1587ms 61.8863 Ops/s 60.3368 Ops/s $\color{#35bf28}+2.57\%$
test_cql_speed[True-backward] 24.4679ms 23.6052ms 42.3636 Ops/s 41.6444 Ops/s $\color{#35bf28}+1.73\%$
test_cql_speed[reduce-overhead-None] 16.8551ms 16.0642ms 62.2501 Ops/s 59.0326 Ops/s $\textbf{\color{#35bf28}+5.45\%}$
test_cql_speed[reduce-overhead-backward] 24.4741ms 23.1900ms 43.1220 Ops/s 41.4692 Ops/s $\color{#35bf28}+3.99\%$
test_a2c_speed[False-None] 8.1893ms 7.4216ms 134.7414 Ops/s 125.4965 Ops/s $\textbf{\color{#35bf28}+7.37\%}$
test_a2c_speed[False-backward] 17.0397ms 15.1838ms 65.8596 Ops/s 64.7248 Ops/s $\color{#35bf28}+1.75\%$
test_a2c_speed[True-None] 3.7799ms 3.3836ms 295.5390 Ops/s 286.9120 Ops/s $\color{#35bf28}+3.01\%$
test_a2c_speed[True-backward] 11.6960ms 10.3920ms 96.2280 Ops/s 91.2331 Ops/s $\textbf{\color{#35bf28}+5.47\%}$
test_a2c_speed[reduce-overhead-None] 4.0713ms 3.4205ms 292.3550 Ops/s 285.2753 Ops/s $\color{#35bf28}+2.48\%$
test_a2c_speed[reduce-overhead-backward] 10.7547ms 10.3474ms 96.6425 Ops/s 89.8111 Ops/s $\textbf{\color{#35bf28}+7.61\%}$
test_ppo_speed[False-None] 8.8899ms 7.7385ms 129.2246 Ops/s 122.7920 Ops/s $\textbf{\color{#35bf28}+5.24\%}$
test_ppo_speed[False-backward] 16.3064ms 15.5678ms 64.2352 Ops/s 59.2484 Ops/s $\textbf{\color{#35bf28}+8.42\%}$
test_ppo_speed[True-None] 4.7852ms 3.8954ms 256.7107 Ops/s 254.1640 Ops/s $\color{#35bf28}+1.00\%$
test_ppo_speed[True-backward] 10.7387ms 10.3674ms 96.4561 Ops/s 91.5254 Ops/s $\textbf{\color{#35bf28}+5.39\%}$
test_ppo_speed[reduce-overhead-None] 4.7447ms 4.0104ms 249.3547 Ops/s 250.0576 Ops/s $\color{#d91a1a}-0.28\%$
test_ppo_speed[reduce-overhead-backward] 10.8915ms 10.2029ms 98.0112 Ops/s 90.8633 Ops/s $\textbf{\color{#35bf28}+7.87\%}$
test_reinforce_speed[False-None] 8.4487ms 6.6573ms 150.2119 Ops/s 143.0408 Ops/s $\textbf{\color{#35bf28}+5.01\%}$
test_reinforce_speed[False-backward] 10.9604ms 10.1928ms 98.1085 Ops/s 93.3483 Ops/s $\textbf{\color{#35bf28}+5.10\%}$
test_reinforce_speed[True-None] 3.7278ms 2.9843ms 335.0890 Ops/s 332.2873 Ops/s $\color{#35bf28}+0.84\%$
test_reinforce_speed[True-backward] 10.0365ms 9.1892ms 108.8232 Ops/s 105.3244 Ops/s $\color{#35bf28}+3.32\%$
test_reinforce_speed[reduce-overhead-None] 3.5740ms 2.8385ms 352.2989 Ops/s 341.1488 Ops/s $\color{#35bf28}+3.27\%$
test_reinforce_speed[reduce-overhead-backward] 10.4725ms 9.3339ms 107.1366 Ops/s 107.1419 Ops/s $-0.00\%$
test_iql_speed[False-None] 35.3518ms 33.2434ms 30.0811 Ops/s 29.9111 Ops/s $\color{#35bf28}+0.57\%$
test_iql_speed[False-backward] 48.7439ms 46.5539ms 21.4805 Ops/s 21.1948 Ops/s $\color{#35bf28}+1.35\%$
test_iql_speed[True-None] 15.0794ms 14.0750ms 71.0481 Ops/s 69.7947 Ops/s $\color{#35bf28}+1.80\%$
test_iql_speed[True-backward] 27.7844ms 25.7342ms 38.8588 Ops/s 37.2061 Ops/s $\color{#35bf28}+4.44\%$
test_iql_speed[reduce-overhead-None] 15.2303ms 14.2277ms 70.2854 Ops/s 69.0763 Ops/s $\color{#35bf28}+1.75\%$
test_iql_speed[reduce-overhead-backward] 27.5313ms 26.3026ms 38.0191 Ops/s 38.0368 Ops/s $\color{#d91a1a}-0.05\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 12.7056ms 5.9020ms 169.4348 Ops/s 177.8353 Ops/s $\color{#d91a1a}-4.72\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.7147ms 0.4976ms 2.0097 KOps/s 2.0333 KOps/s $\color{#d91a1a}-1.16\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7162ms 0.4590ms 2.1785 KOps/s 2.0634 KOps/s $\textbf{\color{#35bf28}+5.58\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 8.0270ms 5.6039ms 178.4463 Ops/s 175.4425 Ops/s $\color{#35bf28}+1.71\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1097ms 0.4946ms 2.0218 KOps/s 2.0362 KOps/s $\color{#d91a1a}-0.71\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 1.1715ms 0.4662ms 2.1452 KOps/s 2.1584 KOps/s $\color{#d91a1a}-0.61\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7903ms 1.5862ms 630.4276 Ops/s 610.9441 Ops/s $\color{#35bf28}+3.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.8231ms 1.5436ms 647.8429 Ops/s 636.6822 Ops/s $\color{#35bf28}+1.75\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 8.0891ms 5.6994ms 175.4572 Ops/s 162.8434 Ops/s $\textbf{\color{#35bf28}+7.75\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.5522ms 0.6441ms 1.5526 KOps/s 1.5270 KOps/s $\color{#35bf28}+1.68\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8988ms 0.5991ms 1.6691 KOps/s 1.6151 KOps/s $\color{#35bf28}+3.34\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 8.3432ms 5.4046ms 185.0274 Ops/s 174.7683 Ops/s $\textbf{\color{#35bf28}+5.87\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.4182ms 0.4941ms 2.0237 KOps/s 1.9723 KOps/s $\color{#35bf28}+2.60\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 1.0099ms 0.4726ms 2.1159 KOps/s 2.0838 KOps/s $\color{#35bf28}+1.54\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3687ms 5.5026ms 181.7338 Ops/s 174.0914 Ops/s $\color{#35bf28}+4.39\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6900ms 0.4879ms 2.0498 KOps/s 1.9835 KOps/s $\color{#35bf28}+3.34\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 8.0352ms 0.4855ms 2.0598 KOps/s 2.1041 KOps/s $\color{#d91a1a}-2.10\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.1830ms 5.6466ms 177.0970 Ops/s 168.9584 Ops/s $\color{#35bf28}+4.82\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.4190ms 0.6417ms 1.5584 KOps/s 1.5640 KOps/s $\color{#d91a1a}-0.35\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0991ms 0.6154ms 1.6250 KOps/s 1.6007 KOps/s $\color{#35bf28}+1.52\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.3104ms 4.5122ms 221.6224 Ops/s 211.8432 Ops/s $\color{#35bf28}+4.62\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 7.6956ms 2.2917ms 436.3625 Ops/s 507.3623 Ops/s $\textbf{\color{#d91a1a}-13.99\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.0487ms 1.2151ms 822.9677 Ops/s 761.2114 Ops/s $\textbf{\color{#35bf28}+8.11\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.5105s 14.7577ms 67.7614 Ops/s 214.0743 Ops/s $\textbf{\color{#d91a1a}-68.35\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 3.6284ms 2.0693ms 483.2494 Ops/s 386.7183 Ops/s $\textbf{\color{#35bf28}+24.96\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.4489ms 1.3240ms 755.3127 Ops/s 786.3530 Ops/s $\color{#d91a1a}-3.95\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.9301ms 4.9734ms 201.0700 Ops/s 28.8062 Ops/s $\textbf{\color{#35bf28}+598.01\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.4457ms 2.5906ms 386.0065 Ops/s 357.5715 Ops/s $\textbf{\color{#35bf28}+7.95\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.0764ms 1.3557ms 737.6254 Ops/s 622.2883 Ops/s $\textbf{\color{#35bf28}+18.53\%}$

@github-actions GitHub Actions
Copy link

github-actions bot commented Sep 30, 2024 •
edited
Loading

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}28$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1064s 0.1041s 9.6087 Ops/s 9.4262 Ops/s $\color{#35bf28}+1.94\%$
test_sync 93.9899ms 91.4475ms 10.9352 Ops/s 10.9863 Ops/s $\color{#d91a1a}-0.46\%$
test_async 0.1710s 86.4144ms 11.5721 Ops/s 11.6269 Ops/s $\color{#d91a1a}-0.47\%$
test_single_pixels 0.1115s 0.1094s 9.1414 Ops/s 9.1764 Ops/s $\color{#d91a1a}-0.38\%$
test_sync_pixels 72.5625ms 71.4720ms 13.9915 Ops/s 13.8629 Ops/s $\color{#35bf28}+0.93\%$
test_async_pixels 0.1334s 67.2763ms 14.8641 Ops/s 14.9172 Ops/s $\color{#d91a1a}-0.36\%$
test_simple 0.7323s 0.7320s 1.3661 Ops/s 1.3321 Ops/s $\color{#35bf28}+2.55\%$
test_transformed 0.9618s 0.9613s 1.0402 Ops/s 1.0462 Ops/s $\color{#d91a1a}-0.57\%$
test_serial 2.1753s 2.1005s 0.4761 Ops/s 0.4756 Ops/s $\color{#35bf28}+0.10\%$
test_parallel 1.9562s 1.8821s 0.5313 Ops/s 0.5287 Ops/s $\color{#35bf28}+0.50\%$
test_step_mdp_speed[True-True-True-True-True] 0.4278ms 38.0394μs 26.2885 KOps/s 27.0334 KOps/s $\color{#d91a1a}-2.76\%$
test_step_mdp_speed[True-True-True-True-False] 0.3898ms 21.3686μs 46.7976 KOps/s 47.3573 KOps/s $\color{#d91a1a}-1.18\%$
test_step_mdp_speed[True-True-True-False-True] 58.5010μs 21.0862μs 47.4245 KOps/s 47.8610 KOps/s $\color{#d91a1a}-0.91\%$
test_step_mdp_speed[True-True-True-False-False] 0.3939ms 12.0756μs 82.8115 KOps/s 83.4750 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-True-False-True-True] 0.4181ms 39.0255μs 25.6242 KOps/s 25.8333 KOps/s $\color{#d91a1a}-0.81\%$
test_step_mdp_speed[True-True-False-True-False] 57.3220μs 23.2877μs 42.9411 KOps/s 43.4212 KOps/s $\color{#d91a1a}-1.11\%$
test_step_mdp_speed[True-True-False-False-True] 0.4042ms 22.8103μs 43.8399 KOps/s 43.4435 KOps/s $\color{#35bf28}+0.91\%$
test_step_mdp_speed[True-True-False-False-False] 0.4142ms 14.3527μs 69.6735 KOps/s 70.5377 KOps/s $\color{#d91a1a}-1.23\%$
test_step_mdp_speed[True-False-True-True-True] 0.4202ms 41.6201μs 24.0268 KOps/s 24.3691 KOps/s $\color{#d91a1a}-1.40\%$
test_step_mdp_speed[True-False-True-True-False] 52.6620μs 25.6054μs 39.0543 KOps/s 39.5162 KOps/s $\color{#d91a1a}-1.17\%$
test_step_mdp_speed[True-False-True-False-True] 0.4027ms 22.8408μs 43.7813 KOps/s 43.1743 KOps/s $\color{#35bf28}+1.41\%$
test_step_mdp_speed[True-False-True-False-False] 0.3938ms 14.0488μs 71.1803 KOps/s 71.0376 KOps/s $\color{#35bf28}+0.20\%$
test_step_mdp_speed[True-False-False-True-True] 0.4261ms 42.7823μs 23.3742 KOps/s 23.0116 KOps/s $\color{#35bf28}+1.58\%$
test_step_mdp_speed[True-False-False-True-False] 59.5410μs 27.1905μs 36.7776 KOps/s 36.3735 KOps/s $\color{#35bf28}+1.11\%$
test_step_mdp_speed[True-False-False-False-True] 0.4021ms 24.7345μs 40.4294 KOps/s 39.8297 KOps/s $\color{#35bf28}+1.51\%$
test_step_mdp_speed[True-False-False-False-False] 0.3958ms 16.1538μs 61.9049 KOps/s 62.7488 KOps/s $\color{#d91a1a}-1.34\%$
test_step_mdp_speed[False-True-True-True-True] 73.5410μs 41.2601μs 24.2365 KOps/s 24.0586 KOps/s $\color{#35bf28}+0.74\%$
test_step_mdp_speed[False-True-True-True-False] 0.4058ms 25.2996μs 39.5263 KOps/s 39.0762 KOps/s $\color{#35bf28}+1.15\%$
test_step_mdp_speed[False-True-True-False-True] 0.4029ms 26.1941μs 38.1765 KOps/s 38.1287 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[False-True-True-False-False] 0.3897ms 15.7594μs 63.4543 KOps/s 64.6465 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[False-True-False-True-True] 72.7520μs 43.1968μs 23.1498 KOps/s 23.1289 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[False-True-False-True-False] 0.4040ms 27.4858μs 36.3824 KOps/s 36.8658 KOps/s $\color{#d91a1a}-1.31\%$
test_step_mdp_speed[False-True-False-False-True] 3.4630ms 28.6183μs 34.9427 KOps/s 35.2583 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[False-True-False-False-False] 0.3967ms 18.0742μs 55.3276 KOps/s 57.3580 KOps/s $\color{#d91a1a}-3.54\%$
test_step_mdp_speed[False-False-True-True-True] 92.2220μs 46.0184μs 21.7304 KOps/s 22.0345 KOps/s $\color{#d91a1a}-1.38\%$
test_step_mdp_speed[False-False-True-True-False] 0.4065ms 28.7076μs 34.8339 KOps/s 34.0108 KOps/s $\color{#35bf28}+2.42\%$
test_step_mdp_speed[False-False-True-False-True] 62.1220μs 28.1231μs 35.5579 KOps/s 35.3286 KOps/s $\color{#35bf28}+0.65\%$
test_step_mdp_speed[False-False-True-False-False] 43.9810μs 17.8066μs 56.1588 KOps/s 57.0042 KOps/s $\color{#d91a1a}-1.48\%$
test_step_mdp_speed[False-False-False-True-True] 80.4520μs 46.8906μs 21.3263 KOps/s 21.2868 KOps/s $\color{#35bf28}+0.19\%$
test_step_mdp_speed[False-False-False-True-False] 58.4120μs 31.6391μs 31.6064 KOps/s 31.6618 KOps/s $\color{#d91a1a}-0.17\%$
test_step_mdp_speed[False-False-False-False-True] 59.4210μs 29.5610μs 33.8283 KOps/s 33.9954 KOps/s $\color{#d91a1a}-0.49\%$
test_step_mdp_speed[False-False-False-False-False] 46.5610μs 19.7982μs 50.5096 KOps/s 51.2801 KOps/s $\color{#d91a1a}-1.50\%$
test_values[generalized_advantage_estimate-True-True] 25.5995ms 25.2766ms 39.5623 Ops/s 39.7269 Ops/s $\color{#d91a1a}-0.41\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1047s 2.9791ms 335.6725 Ops/s 315.4985 Ops/s $\textbf{\color{#35bf28}+6.39\%}$
test_values[td0_return_estimate-False-False] 88.7220μs 66.4148μs 15.0569 KOps/s 14.9701 KOps/s $\color{#35bf28}+0.58\%$
test_values[td1_return_estimate-False-False] 56.3608ms 56.1392ms 17.8129 Ops/s 17.8724 Ops/s $\color{#d91a1a}-0.33\%$
test_values[vec_td1_return_estimate-False-False] 1.3715ms 1.0690ms 935.4888 Ops/s 931.3111 Ops/s $\color{#35bf28}+0.45\%$
test_values[td_lambda_return_estimate-True-False] 89.0511ms 88.6718ms 11.2775 Ops/s 11.0898 Ops/s $\color{#35bf28}+1.69\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3983ms 1.0695ms 935.0598 Ops/s 933.7141 Ops/s $\color{#35bf28}+0.14\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.3382ms 25.1954ms 39.6897 Ops/s 37.8962 Ops/s $\color{#35bf28}+4.73\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9433ms 0.7235ms 1.3822 KOps/s 1.3836 KOps/s $\color{#d91a1a}-0.10\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7779ms 0.6558ms 1.5249 KOps/s 1.5174 KOps/s $\color{#35bf28}+0.49\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.4969ms 1.4636ms 683.2380 Ops/s 682.2750 Ops/s $\color{#35bf28}+0.14\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7168ms 0.6729ms 1.4862 KOps/s 1.4810 KOps/s $\color{#35bf28}+0.35\%$
test_dqn_speed[False-None] 6.9885ms 1.3337ms 749.8161 Ops/s 756.6497 Ops/s $\color{#d91a1a}-0.90\%$
test_dqn_speed[False-backward] 1.9212ms 1.8239ms 548.2768 Ops/s 552.1311 Ops/s $\color{#d91a1a}-0.70\%$
test_dqn_speed[True-None] 0.6783ms 0.5616ms 1.7805 KOps/s 1.8238 KOps/s $\color{#d91a1a}-2.37\%$
test_dqn_speed[True-backward] 1.0391ms 0.9883ms 1.0118 KOps/s 927.8229 Ops/s $\textbf{\color{#35bf28}+9.05\%}$
test_dqn_speed[reduce-overhead-None] 0.6971ms 0.5688ms 1.7581 KOps/s 1.7965 KOps/s $\color{#d91a1a}-2.14\%$
test_dqn_speed[reduce-overhead-backward] 1.0475ms 0.9925ms 1.0076 KOps/s 999.9969 Ops/s $\color{#35bf28}+0.76\%$
test_ddpg_speed[False-None] 3.1368ms 2.6852ms 372.4151 Ops/s 373.7334 Ops/s $\color{#d91a1a}-0.35\%$
test_ddpg_speed[False-backward] 4.1263ms 3.8926ms 256.8992 Ops/s 255.6450 Ops/s $\color{#35bf28}+0.49\%$
test_ddpg_speed[True-None] 1.6144ms 1.2431ms 804.4146 Ops/s 806.6055 Ops/s $\color{#d91a1a}-0.27\%$
test_ddpg_speed[True-backward] 2.2982ms 2.2125ms 451.9827 Ops/s 447.3380 Ops/s $\color{#35bf28}+1.04\%$
test_ddpg_speed[reduce-overhead-None] 1.6077ms 1.2418ms 805.3066 Ops/s 797.3868 Ops/s $\color{#35bf28}+0.99\%$
test_ddpg_speed[reduce-overhead-backward] 2.2880ms 2.2139ms 451.6960 Ops/s 454.3594 Ops/s $\color{#d91a1a}-0.59\%$
test_sac_speed[False-None] 8.3284ms 7.4429ms 134.3567 Ops/s 133.3797 Ops/s $\color{#35bf28}+0.73\%$
test_sac_speed[False-backward] 11.1043ms 10.6406ms 93.9794 Ops/s 93.9773 Ops/s $+0.00\%$
test_sac_speed[True-None] 2.4221ms 1.9966ms 500.8500 Ops/s 497.0461 Ops/s $\color{#35bf28}+0.77\%$
test_sac_speed[True-backward] 4.2525ms 3.9249ms 254.7855 Ops/s 233.3335 Ops/s $\textbf{\color{#35bf28}+9.19\%}$
test_sac_speed[reduce-overhead-None] 2.3823ms 2.0048ms 498.7981 Ops/s 497.7175 Ops/s $\color{#35bf28}+0.22\%$
test_sac_speed[reduce-overhead-backward] 3.9500ms 3.8807ms 257.6853 Ops/s 256.1084 Ops/s $\color{#35bf28}+0.62\%$
test_redq_speed[False-None] 0.2579s 12.6675ms 78.9421 Ops/s 101.1205 Ops/s $\textbf{\color{#d91a1a}-21.93\%}$
test_redq_speed[False-backward] 21.9930ms 17.5448ms 56.9970 Ops/s 58.9072 Ops/s $\color{#d91a1a}-3.24\%$
test_redq_speed[True-None] 3.7735ms 3.3549ms 298.0753 Ops/s 302.7433 Ops/s $\color{#d91a1a}-1.54\%$
test_redq_speed[True-backward] 8.4579ms 8.1251ms 123.0753 Ops/s 124.8169 Ops/s $\color{#d91a1a}-1.40\%$
test_redq_speed[reduce-overhead-None] 3.7914ms 3.3791ms 295.9403 Ops/s 298.1037 Ops/s $\color{#d91a1a}-0.73\%$
test_redq_speed[reduce-overhead-backward] 8.7001ms 8.1440ms 122.7904 Ops/s 126.4532 Ops/s $\color{#d91a1a}-2.90\%$
test_redq_deprec_speed[False-None] 10.7920ms 10.2739ms 97.3340 Ops/s 96.5956 Ops/s $\color{#35bf28}+0.76\%$
test_redq_deprec_speed[False-backward] 15.2958ms 14.7227ms 67.9224 Ops/s 67.5200 Ops/s $\color{#35bf28}+0.60\%$
test_redq_deprec_speed[True-None] 3.3068ms 3.0992ms 322.6607 Ops/s 282.6446 Ops/s $\textbf{\color{#35bf28}+14.16\%}$
test_redq_deprec_speed[True-backward] 6.7635ms 6.5992ms 151.5329 Ops/s 139.5954 Ops/s $\textbf{\color{#35bf28}+8.55\%}$
test_redq_deprec_speed[reduce-overhead-None] 3.6527ms 3.1141ms 321.1228 Ops/s 297.7413 Ops/s $\textbf{\color{#35bf28}+7.85\%}$
test_redq_deprec_speed[reduce-overhead-backward] 6.9054ms 6.5404ms 152.8957 Ops/s 137.5066 Ops/s $\textbf{\color{#35bf28}+11.19\%}$
test_td3_speed[False-None] 7.7659ms 7.4215ms 134.7439 Ops/s 133.4146 Ops/s $\color{#35bf28}+1.00\%$
test_td3_speed[False-backward] 10.6303ms 10.1882ms 98.1526 Ops/s 96.8472 Ops/s $\color{#35bf28}+1.35\%$
test_td3_speed[True-None] 2.3337ms 2.0675ms 483.6843 Ops/s 480.7747 Ops/s $\color{#35bf28}+0.61\%$
test_td3_speed[True-backward] 4.0283ms 3.8765ms 257.9627 Ops/s 257.1916 Ops/s $\color{#35bf28}+0.30\%$
test_td3_speed[reduce-overhead-None] 2.1689ms 2.0354ms 491.3119 Ops/s 488.6420 Ops/s $\color{#35bf28}+0.55\%$
test_td3_speed[reduce-overhead-backward] 3.9850ms 3.8817ms 257.6222 Ops/s 261.8186 Ops/s $\color{#d91a1a}-1.60\%$
test_cql_speed[False-None] 29.0248ms 24.3650ms 41.0425 Ops/s 41.5173 Ops/s $\color{#d91a1a}-1.14\%$
test_cql_speed[False-backward] 35.9479ms 32.9930ms 30.3095 Ops/s 30.3312 Ops/s $\color{#d91a1a}-0.07\%$
test_cql_speed[True-None] 10.9635ms 10.6299ms 94.0741 Ops/s 94.0448 Ops/s $\color{#35bf28}+0.03\%$
test_cql_speed[True-backward] 16.4054ms 16.0048ms 62.4812 Ops/s 61.7606 Ops/s $\color{#35bf28}+1.17\%$
test_cql_speed[reduce-overhead-None] 10.9076ms 10.6696ms 93.7247 Ops/s 93.4294 Ops/s $\color{#35bf28}+0.32\%$
test_cql_speed[reduce-overhead-backward] 16.7790ms 16.1991ms 61.7317 Ops/s 60.8338 Ops/s $\color{#35bf28}+1.48\%$
test_a2c_speed[False-None] 5.5958ms 5.1535ms 194.0445 Ops/s 187.6882 Ops/s $\color{#35bf28}+3.39\%$
test_a2c_speed[False-backward] 11.7444ms 11.2894ms 88.5790 Ops/s 86.0250 Ops/s $\color{#35bf28}+2.97\%$
test_a2c_speed[True-None] 3.3667ms 3.0075ms 332.5034 Ops/s 326.8962 Ops/s $\color{#35bf28}+1.72\%$
test_a2c_speed[True-backward] 8.6181ms 8.3856ms 119.2516 Ops/s 112.7543 Ops/s $\textbf{\color{#35bf28}+5.76\%}$
test_a2c_speed[reduce-overhead-None] 3.1273ms 2.9980ms 333.5535 Ops/s 332.5817 Ops/s $\color{#35bf28}+0.29\%$
test_a2c_speed[reduce-overhead-backward] 8.5914ms 8.3779ms 119.3623 Ops/s 119.0194 Ops/s $\color{#35bf28}+0.29\%$
test_ppo_speed[False-None] 5.7150ms 5.5580ms 179.9213 Ops/s 177.2541 Ops/s $\color{#35bf28}+1.50\%$
test_ppo_speed[False-backward] 12.1193ms 11.8637ms 84.2905 Ops/s 83.6081 Ops/s $\color{#35bf28}+0.82\%$
test_ppo_speed[True-None] 3.8345ms 3.3975ms 294.3361 Ops/s 279.2004 Ops/s $\textbf{\color{#35bf28}+5.42\%}$
test_ppo_speed[True-backward] 8.2329ms 8.0374ms 124.4185 Ops/s 113.3772 Ops/s $\textbf{\color{#35bf28}+9.74\%}$
test_ppo_speed[reduce-overhead-None] 3.7959ms 3.3949ms 294.5615 Ops/s 298.5375 Ops/s $\color{#d91a1a}-1.33\%$
test_ppo_speed[reduce-overhead-backward] 8.3701ms 8.0910ms 123.5938 Ops/s 123.5568 Ops/s $\color{#35bf28}+0.03\%$
test_reinforce_speed[False-None] 4.6783ms 4.3106ms 231.9882 Ops/s 225.7642 Ops/s $\color{#35bf28}+2.76\%$
test_reinforce_speed[False-backward] 7.2026ms 7.0167ms 142.5163 Ops/s 138.4328 Ops/s $\color{#35bf28}+2.95\%$
test_reinforce_speed[True-None] 2.6266ms 2.1746ms 459.8612 Ops/s 460.2157 Ops/s $\color{#d91a1a}-0.08\%$
test_reinforce_speed[True-backward] 7.1256ms 6.9038ms 144.8481 Ops/s 144.6248 Ops/s $\color{#35bf28}+0.15\%$
test_reinforce_speed[reduce-overhead-None] 2.6187ms 2.1639ms 462.1342 Ops/s 452.1490 Ops/s $\color{#35bf28}+2.21\%$
test_reinforce_speed[reduce-overhead-backward] 7.3886ms 6.9211ms 144.4860 Ops/s 144.3349 Ops/s $\color{#35bf28}+0.10\%$
test_iql_speed[False-None] 20.2319ms 18.6611ms 53.5875 Ops/s 50.9424 Ops/s $\textbf{\color{#35bf28}+5.19\%}$
test_iql_speed[False-backward] 29.1309ms 28.6271ms 34.9320 Ops/s 33.9573 Ops/s $\color{#35bf28}+2.87\%$
test_iql_speed[True-None] 8.0894ms 7.6404ms 130.8827 Ops/s 126.9763 Ops/s $\color{#35bf28}+3.08\%$
test_iql_speed[True-backward] 16.5996ms 16.1147ms 62.0550 Ops/s 59.6738 Ops/s $\color{#35bf28}+3.99\%$
test_iql_speed[reduce-overhead-None] 8.1557ms 7.6204ms 131.2271 Ops/s 130.9650 Ops/s $\color{#35bf28}+0.20\%$
test_iql_speed[reduce-overhead-backward] 16.4732ms 16.1095ms 62.0753 Ops/s 61.5313 Ops/s $\color{#35bf28}+0.88\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.2466ms 6.8416ms 146.1652 Ops/s 145.7297 Ops/s $\color{#35bf28}+0.30\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5216ms 0.2381ms 4.1996 KOps/s 3.1413 KOps/s $\textbf{\color{#35bf28}+33.69\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6335ms 0.2153ms 4.6442 KOps/s 3.3197 KOps/s $\textbf{\color{#35bf28}+39.90\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.1478ms 6.6667ms 149.9987 Ops/s 148.5494 Ops/s $\color{#35bf28}+0.98\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6417ms 0.2352ms 4.2515 KOps/s 3.0313 KOps/s $\textbf{\color{#35bf28}+40.25\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6232ms 0.2136ms 4.6809 KOps/s 3.2148 KOps/s $\textbf{\color{#35bf28}+45.60\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6105ms 1.2019ms 832.0190 Ops/s 728.5640 Ops/s $\textbf{\color{#35bf28}+14.20\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.3575ms 1.1551ms 865.7581 Ops/s 806.4467 Ops/s $\textbf{\color{#35bf28}+7.35\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.3045ms 6.9077ms 144.7659 Ops/s 145.9383 Ops/s $\color{#d91a1a}-0.80\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0488ms 0.4358ms 2.2947 KOps/s 2.0444 KOps/s $\textbf{\color{#35bf28}+12.24\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8844ms 0.4066ms 2.4592 KOps/s 2.3644 KOps/s $\color{#35bf28}+4.01\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.2173ms 6.7798ms 147.4973 Ops/s 148.7768 Ops/s $\color{#d91a1a}-0.86\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8207ms 0.2528ms 3.9553 KOps/s 2.8111 KOps/s $\textbf{\color{#35bf28}+40.70\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5258ms 0.2414ms 4.1420 KOps/s 3.1620 KOps/s $\textbf{\color{#35bf28}+30.99\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.1125ms 6.7847ms 147.3899 Ops/s 150.7557 Ops/s $\color{#d91a1a}-2.23\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6570ms 0.2414ms 4.1422 KOps/s 3.1011 KOps/s $\textbf{\color{#35bf28}+33.57\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4953ms 0.2324ms 4.3037 KOps/s 3.9395 KOps/s $\textbf{\color{#35bf28}+9.25\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.0429ms 6.9123ms 144.6705 Ops/s 146.0384 Ops/s $\color{#d91a1a}-0.94\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.2747ms 0.3782ms 2.6439 KOps/s 2.5130 KOps/s $\textbf{\color{#35bf28}+5.21\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.5853ms 0.3687ms 2.7119 KOps/s 2.5673 KOps/s $\textbf{\color{#35bf28}+5.63\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.7480ms 5.2613ms 190.0666 Ops/s 34.7016 Ops/s $\textbf{\color{#35bf28}+447.72\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 6.2759ms 1.7200ms 581.3841 Ops/s 662.6658 Ops/s $\textbf{\color{#d91a1a}-12.27\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.1608ms 1.0467ms 955.3651 Ops/s 815.3059 Ops/s $\textbf{\color{#35bf28}+17.18\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4080s 13.3972ms 74.6426 Ops/s 183.7351 Ops/s $\textbf{\color{#d91a1a}-59.37\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 8.8666ms 1.8496ms 540.6711 Ops/s 513.9515 Ops/s $\textbf{\color{#35bf28}+5.20\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.0998ms 0.9504ms 1.0522 KOps/s 765.7342 Ops/s $\textbf{\color{#35bf28}+37.40\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 7.1228ms 5.5210ms 181.1251 Ops/s 179.5737 Ops/s $\color{#35bf28}+0.86\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.8885ms 2.1590ms 463.1689 Ops/s 486.7673 Ops/s $\color{#d91a1a}-4.85\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.8059ms 1.3809ms 724.1422 Ops/s 708.7483 Ops/s $\color{#35bf28}+2.17\%$

@thomasbbrunner
Copy link
Contributor

Really nice addition to the docs!

@vmoens vmoens added the documentation Improvements or additions to documentation label Sep 30, 2024
@vmoens
Update
8caa4f8 
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Sep 30, 2024
@vmoens
[Doc] Better doc for inverse transform semantic
18f058b 
ghstack-source-id: 1a39086305be86612bb63cf64b9ad807d9801378
Pull Request resolved: #2459
@vmoens
Update
7ef7a55 
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Sep 30, 2024
@vmoens
[Doc] Better doc for inverse transform semantic
f306e07 
ghstack-source-id: a4676b2a1ce85c0837a0598c6a868fa354925ed1
Pull Request resolved: #2459
@vmoens
Update
07c7eef 
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Sep 30, 2024
@vmoens
[Doc] Better doc for inverse transform semantic
c619571 
ghstack-source-id: 444ad87d1ab0a829e8ce1848b5838859d5ee7494
Pull Request resolved: #2459
@vmoens vmoens merged commit 07c7eef into gh/vmoens/30/base Sep 30, 2024
9 of 14 checks passed
vmoens added a commit that referenced this pull request Sep 30, 2024
@vmoens
[Doc] Better doc for inverse transform semantic
6d1a1b3 
ghstack-source-id: 444ad87d1ab0a829e8ce1848b5838859d5ee7494
Pull Request resolved: #2459
@vmoens vmoens deleted the gh/vmoens/30/head branch September 30, 2024 14:07
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. documentation Improvements or additions to documentation
Projects
None yet
Milestone
No milestone
Development

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