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.

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

[BugFix] Fix OOB TruncatedNormal LP #1924

Merged
merged 1 commit into from
Feb 17, 2024
Merged

[BugFix] Fix OOB TruncatedNormal LP #1924

merged 1 commit into from
Feb 17, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 17, 2024

No description provided.

Copy link

pytorch-bot bot commented Feb 17, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1924

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

❌ 5 New Failures, 22 Unrelated Failures

As of commit e815532 with merge base e538fdc (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

BROKEN TRUNK - The following job 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.

@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 Feb 17, 2024
@vmoens vmoens added bug Something isn't working Suitable for minor Suitable to be integrated in minor release (no new feature) and removed CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. labels Feb 17, 2024
@vmoens vmoens merged commit d68a900 into main Feb 17, 2024
34 of 53 checks passed
@vmoens vmoens deleted the fix-trunc-normal branch February 17, 2024 21:20
Copy link

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}9$. Worsened: $\large\color{#d91a1a}1$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 63.1659ms 62.4377ms 16.0160 Ops/s 16.1810 Ops/s $\color{#d91a1a}-1.02\%$
test_sync 39.7257ms 33.5676ms 29.7906 Ops/s 29.3469 Ops/s $\color{#35bf28}+1.51\%$
test_async 0.1388s 33.2680ms 30.0589 Ops/s 30.2230 Ops/s $\color{#d91a1a}-0.54\%$
test_simple 0.5030s 0.4362s 2.2925 Ops/s 2.2848 Ops/s $\color{#35bf28}+0.34\%$
test_transformed 0.6545s 0.5942s 1.6829 Ops/s 1.6829 Ops/s $+0.00\%$
test_serial 1.4810s 1.4181s 0.7052 Ops/s 0.7005 Ops/s $\color{#35bf28}+0.67\%$
test_parallel 1.4115s 1.3462s 0.7428 Ops/s 0.7188 Ops/s $\color{#35bf28}+3.35\%$
test_step_mdp_speed[True-True-True-True-True] 0.1446ms 21.4999μs 46.5119 KOps/s 46.6195 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[True-True-True-True-False] 38.5310μs 13.0932μs 76.3754 KOps/s 78.2720 KOps/s $\color{#d91a1a}-2.42\%$
test_step_mdp_speed[True-True-True-False-True] 45.7550μs 12.4586μs 80.2656 KOps/s 80.6363 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[True-True-True-False-False] 29.1840μs 7.6879μs 130.0753 KOps/s 133.0187 KOps/s $\color{#d91a1a}-2.21\%$
test_step_mdp_speed[True-True-False-True-True] 49.1920μs 22.7241μs 44.0061 KOps/s 44.2203 KOps/s $\color{#d91a1a}-0.48\%$
test_step_mdp_speed[True-True-False-True-False] 34.9050μs 14.4126μs 69.3835 KOps/s 71.3354 KOps/s $\color{#d91a1a}-2.74\%$
test_step_mdp_speed[True-True-False-False-True] 41.1370μs 13.6982μs 73.0024 KOps/s 74.5696 KOps/s $\color{#d91a1a}-2.10\%$
test_step_mdp_speed[True-True-False-False-False] 47.6490μs 8.9001μs 112.3584 KOps/s 115.5991 KOps/s $\color{#d91a1a}-2.80\%$
test_step_mdp_speed[True-False-True-True-True] 60.2220μs 23.9631μs 41.7308 KOps/s 42.0519 KOps/s $\color{#d91a1a}-0.76\%$
test_step_mdp_speed[True-False-True-True-False] 47.9990μs 15.5556μs 64.2854 KOps/s 65.1288 KOps/s $\color{#d91a1a}-1.29\%$
test_step_mdp_speed[True-False-True-False-True] 42.8900μs 13.5649μs 73.7197 KOps/s 72.6344 KOps/s $\color{#35bf28}+1.49\%$
test_step_mdp_speed[True-False-True-False-False] 22.4320μs 8.8674μs 112.7729 KOps/s 114.7128 KOps/s $\color{#d91a1a}-1.69\%$
test_step_mdp_speed[True-False-False-True-True] 61.7950μs 25.1331μs 39.7882 KOps/s 40.1755 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[True-False-False-True-False] 51.0550μs 16.8924μs 59.1981 KOps/s 60.9726 KOps/s $\color{#d91a1a}-2.91\%$
test_step_mdp_speed[True-False-False-False-True] 41.0660μs 14.8865μs 67.1751 KOps/s 67.5483 KOps/s $\color{#d91a1a}-0.55\%$
test_step_mdp_speed[True-False-False-False-False] 27.8930μs 10.0683μs 99.3215 KOps/s 101.8032 KOps/s $\color{#d91a1a}-2.44\%$
test_step_mdp_speed[False-True-True-True-True] 48.4200μs 23.9944μs 41.6765 KOps/s 41.9234 KOps/s $\color{#d91a1a}-0.59\%$
test_step_mdp_speed[False-True-True-True-False] 41.5880μs 15.7313μs 63.5677 KOps/s 65.0039 KOps/s $\color{#d91a1a}-2.21\%$
test_step_mdp_speed[False-True-True-False-True] 42.9700μs 15.8912μs 62.9278 KOps/s 62.6959 KOps/s $\color{#35bf28}+0.37\%$
test_step_mdp_speed[False-True-True-False-False] 28.8340μs 9.9574μs 100.4277 KOps/s 100.2993 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[False-True-False-True-True] 51.3960μs 25.4719μs 39.2589 KOps/s 39.7350 KOps/s $\color{#d91a1a}-1.20\%$
test_step_mdp_speed[False-True-False-True-False] 42.5190μs 16.7438μs 59.7236 KOps/s 60.1652 KOps/s $\color{#d91a1a}-0.73\%$
test_step_mdp_speed[False-True-False-False-True] 42.5700μs 17.0885μs 58.5188 KOps/s 58.6062 KOps/s $\color{#d91a1a}-0.15\%$
test_step_mdp_speed[False-True-False-False-False] 60.2330μs 11.1232μs 89.9020 KOps/s 90.5041 KOps/s $\color{#d91a1a}-0.67\%$
test_step_mdp_speed[False-False-True-True-True] 50.1940μs 26.3865μs 37.8982 KOps/s 38.3567 KOps/s $\color{#d91a1a}-1.20\%$
test_step_mdp_speed[False-False-True-True-False] 41.3670μs 18.2608μs 54.7622 KOps/s 56.1977 KOps/s $\color{#d91a1a}-2.55\%$
test_step_mdp_speed[False-False-True-False-True] 44.7930μs 17.2210μs 58.0685 KOps/s 58.3792 KOps/s $\color{#d91a1a}-0.53\%$
test_step_mdp_speed[False-False-True-False-False] 45.2740μs 11.2535μs 88.8615 KOps/s 90.7432 KOps/s $\color{#d91a1a}-2.07\%$
test_step_mdp_speed[False-False-False-True-True] 55.4930μs 27.8007μs 35.9703 KOps/s 36.4281 KOps/s $\color{#d91a1a}-1.26\%$
test_step_mdp_speed[False-False-False-True-False] 46.9880μs 19.2669μs 51.9025 KOps/s 53.3869 KOps/s $\color{#d91a1a}-2.78\%$
test_step_mdp_speed[False-False-False-False-True] 44.7840μs 18.0978μs 55.2554 KOps/s 55.2132 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[False-False-False-False-False] 43.7620μs 12.3198μs 81.1700 KOps/s 81.2822 KOps/s $\color{#d91a1a}-0.14\%$
test_values[generalized_advantage_estimate-True-True] 9.5505ms 9.2261ms 108.3887 Ops/s 106.1512 Ops/s $\color{#35bf28}+2.11\%$
test_values[vec_generalized_advantage_estimate-True-True] 39.3895ms 33.3286ms 30.0043 Ops/s 28.2779 Ops/s $\textbf{\color{#35bf28}+6.11\%}$
test_values[td0_return_estimate-False-False] 0.2199ms 0.1648ms 6.0662 KOps/s 5.7023 KOps/s $\textbf{\color{#35bf28}+6.38\%}$
test_values[td1_return_estimate-False-False] 25.7402ms 22.6324ms 44.1844 Ops/s 42.4128 Ops/s $\color{#35bf28}+4.18\%$
test_values[vec_td1_return_estimate-False-False] 34.5221ms 33.2196ms 30.1027 Ops/s 28.5408 Ops/s $\textbf{\color{#35bf28}+5.47\%}$
test_values[td_lambda_return_estimate-True-False] 35.5881ms 32.8517ms 30.4398 Ops/s 29.2071 Ops/s $\color{#35bf28}+4.22\%$
test_values[vec_td_lambda_return_estimate-True-False] 34.4364ms 33.2301ms 30.0932 Ops/s 28.3659 Ops/s $\textbf{\color{#35bf28}+6.09\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 11.2394ms 7.9862ms 125.2161 Ops/s 121.3349 Ops/s $\color{#35bf28}+3.20\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3057ms 1.9678ms 508.1805 Ops/s 515.9357 Ops/s $\color{#d91a1a}-1.50\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4812ms 0.3482ms 2.8719 KOps/s 2.8039 KOps/s $\color{#35bf28}+2.43\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 49.6984ms 46.8868ms 21.3280 Ops/s 22.1705 Ops/s $\color{#d91a1a}-3.80\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.4935ms 3.0171ms 331.4433 Ops/s 330.4652 Ops/s $\color{#35bf28}+0.30\%$
test_dqn_speed 7.1593ms 1.3465ms 742.6430 Ops/s 732.9443 Ops/s $\color{#35bf28}+1.32\%$
test_ddpg_speed 75.5196ms 2.9074ms 343.9444 Ops/s 348.1439 Ops/s $\color{#d91a1a}-1.21\%$
test_sac_speed 9.7632ms 8.5814ms 116.5311 Ops/s 110.8190 Ops/s $\textbf{\color{#35bf28}+5.15\%}$
test_redq_speed 14.5590ms 13.4588ms 74.3009 Ops/s 73.3592 Ops/s $\color{#35bf28}+1.28\%$
test_redq_deprec_speed 14.9027ms 13.7463ms 72.7468 Ops/s 70.8066 Ops/s $\color{#35bf28}+2.74\%$
test_td3_speed 8.9420ms 8.6295ms 115.8820 Ops/s 113.6792 Ops/s $\color{#35bf28}+1.94\%$
test_cql_speed 38.1275ms 36.9529ms 27.0615 Ops/s 27.0098 Ops/s $\color{#35bf28}+0.19\%$
test_a2c_speed 8.4747ms 7.3619ms 135.8341 Ops/s 132.4110 Ops/s $\color{#35bf28}+2.59\%$
test_ppo_speed 8.2993ms 7.5960ms 131.6486 Ops/s 126.9384 Ops/s $\color{#35bf28}+3.71\%$
test_reinforce_speed 7.6642ms 6.5386ms 152.9375 Ops/s 147.2184 Ops/s $\color{#35bf28}+3.88\%$
test_iql_speed 34.4675ms 33.1662ms 30.1512 Ops/s 29.6624 Ops/s $\color{#35bf28}+1.65\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.1327ms 2.8072ms 356.2328 Ops/s 335.2626 Ops/s $\textbf{\color{#35bf28}+6.25\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8095ms 0.5182ms 1.9299 KOps/s 1.9259 KOps/s $\color{#35bf28}+0.21\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6501ms 0.4843ms 2.0649 KOps/s 2.0305 KOps/s $\color{#35bf28}+1.69\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.0088ms 2.7756ms 360.2885 Ops/s 341.1829 Ops/s $\textbf{\color{#35bf28}+5.60\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8648ms 0.5092ms 1.9638 KOps/s 1.9509 KOps/s $\color{#35bf28}+0.66\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7745ms 0.4875ms 2.0513 KOps/s 2.0443 KOps/s $\color{#35bf28}+0.34\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.2699ms 3.0123ms 331.9753 Ops/s 333.2089 Ops/s $\color{#d91a1a}-0.37\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9604ms 0.6409ms 1.5603 KOps/s 1.5676 KOps/s $\color{#d91a1a}-0.47\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9211ms 0.6087ms 1.6428 KOps/s 1.6340 KOps/s $\color{#35bf28}+0.54\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.1839ms 2.8483ms 351.0900 Ops/s 352.0556 Ops/s $\color{#d91a1a}-0.27\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8262ms 0.5115ms 1.9551 KOps/s 1.9302 KOps/s $\color{#35bf28}+1.29\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7844ms 0.4831ms 2.0698 KOps/s 2.0389 KOps/s $\color{#35bf28}+1.52\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.0157ms 2.7579ms 362.5898 Ops/s 355.5047 Ops/s $\color{#35bf28}+1.99\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6304ms 0.5023ms 1.9908 KOps/s 1.9671 KOps/s $\color{#35bf28}+1.20\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7482ms 0.4819ms 2.0753 KOps/s 2.0692 KOps/s $\color{#35bf28}+0.29\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.0649ms 2.8311ms 353.2182 Ops/s 347.2624 Ops/s $\color{#35bf28}+1.72\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7362ms 0.6233ms 1.6043 KOps/s 1.5843 KOps/s $\color{#35bf28}+1.26\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9131ms 0.5977ms 1.6731 KOps/s 1.6686 KOps/s $\color{#35bf28}+0.27\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 98.1131ms 7.7582ms 128.8965 Ops/s 124.6997 Ops/s $\color{#35bf28}+3.37\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 17.8151ms 13.2053ms 75.7270 Ops/s 76.2703 Ops/s $\color{#d91a1a}-0.71\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 4.4130ms 2.5102ms 398.3744 Ops/s 395.7179 Ops/s $\color{#35bf28}+0.67\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1004s 9.6615ms 103.5039 Ops/s 103.1023 Ops/s $\color{#35bf28}+0.39\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 15.3617ms 12.9628ms 77.1438 Ops/s 76.2871 Ops/s $\color{#35bf28}+1.12\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.9482ms 2.5316ms 395.0090 Ops/s 375.7523 Ops/s $\textbf{\color{#35bf28}+5.12\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 99.0486ms 9.8541ms 101.4811 Ops/s 121.9974 Ops/s $\textbf{\color{#d91a1a}-16.82\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 15.7151ms 13.2081ms 75.7114 Ops/s 65.9157 Ops/s $\textbf{\color{#35bf28}+14.86\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.8446ms 2.7606ms 362.2436 Ops/s 359.4388 Ops/s $\color{#35bf28}+0.78\%$

Copy link

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1138s 0.1124s 8.8978 Ops/s 8.7967 Ops/s $\color{#35bf28}+1.15\%$
test_sync 0.1748s 0.1024s 9.7662 Ops/s 9.7727 Ops/s $\color{#d91a1a}-0.07\%$
test_async 0.2560s 91.0788ms 10.9795 Ops/s 10.9976 Ops/s $\color{#d91a1a}-0.16\%$
test_single_pixels 0.1339s 0.1334s 7.4946 Ops/s 8.0885 Ops/s $\textbf{\color{#d91a1a}-7.34\%}$
test_sync_pixels 82.4465ms 80.0081ms 12.4987 Ops/s 12.4255 Ops/s $\color{#35bf28}+0.59\%$
test_async_pixels 0.2130s 72.8108ms 13.7342 Ops/s 13.6002 Ops/s $\color{#35bf28}+0.99\%$
test_simple 0.8803s 0.8082s 1.2373 Ops/s 1.2693 Ops/s $\color{#d91a1a}-2.52\%$
test_transformed 1.0972s 1.0265s 0.9741 Ops/s 0.9776 Ops/s $\color{#d91a1a}-0.35\%$
test_serial 2.4281s 2.3609s 0.4236 Ops/s 0.4308 Ops/s $\color{#d91a1a}-1.68\%$
test_parallel 2.1587s 2.0748s 0.4820 Ops/s 0.4800 Ops/s $\color{#35bf28}+0.41\%$
test_step_mdp_speed[True-True-True-True-True] 0.1063ms 30.8616μs 32.4027 KOps/s 30.6605 KOps/s $\textbf{\color{#35bf28}+5.68\%}$
test_step_mdp_speed[True-True-True-True-False] 42.0310μs 18.5630μs 53.8707 KOps/s 52.3472 KOps/s $\color{#35bf28}+2.91\%$
test_step_mdp_speed[True-True-True-False-True] 41.2410μs 17.6387μs 56.6935 KOps/s 54.3045 KOps/s $\color{#35bf28}+4.40\%$
test_step_mdp_speed[True-True-True-False-False] 34.4910μs 10.6790μs 93.6418 KOps/s 92.8132 KOps/s $\color{#35bf28}+0.89\%$
test_step_mdp_speed[True-True-False-True-True] 94.3420μs 32.6760μs 30.6035 KOps/s 29.4351 KOps/s $\color{#35bf28}+3.97\%$
test_step_mdp_speed[True-True-False-True-False] 46.6010μs 20.4956μs 48.7909 KOps/s 47.5156 KOps/s $\color{#35bf28}+2.68\%$
test_step_mdp_speed[True-True-False-False-True] 43.2510μs 19.4826μs 51.3278 KOps/s 49.8503 KOps/s $\color{#35bf28}+2.96\%$
test_step_mdp_speed[True-True-False-False-False] 32.5900μs 12.4952μs 80.0310 KOps/s 78.9582 KOps/s $\color{#35bf28}+1.36\%$
test_step_mdp_speed[True-False-True-True-True] 62.5010μs 34.3758μs 29.0902 KOps/s 28.1924 KOps/s $\color{#35bf28}+3.18\%$
test_step_mdp_speed[True-False-True-True-False] 45.6710μs 22.3439μs 44.7549 KOps/s 43.4636 KOps/s $\color{#35bf28}+2.97\%$
test_step_mdp_speed[True-False-True-False-True] 43.7610μs 19.4938μs 51.2983 KOps/s 49.8869 KOps/s $\color{#35bf28}+2.83\%$
test_step_mdp_speed[True-False-True-False-False] 32.2200μs 12.5188μs 79.8796 KOps/s 79.2300 KOps/s $\color{#35bf28}+0.82\%$
test_step_mdp_speed[True-False-False-True-True] 0.2330ms 36.2850μs 27.5596 KOps/s 26.5129 KOps/s $\color{#35bf28}+3.95\%$
test_step_mdp_speed[True-False-False-True-False] 52.1110μs 24.1232μs 41.4538 KOps/s 40.1379 KOps/s $\color{#35bf28}+3.28\%$
test_step_mdp_speed[True-False-False-False-True] 45.8310μs 21.0459μs 47.5152 KOps/s 45.2105 KOps/s $\textbf{\color{#35bf28}+5.10\%}$
test_step_mdp_speed[True-False-False-False-False] 35.9610μs 14.2104μs 70.3710 KOps/s 68.3845 KOps/s $\color{#35bf28}+2.90\%$
test_step_mdp_speed[False-True-True-True-True] 62.3410μs 34.7288μs 28.7946 KOps/s 27.7719 KOps/s $\color{#35bf28}+3.68\%$
test_step_mdp_speed[False-True-True-True-False] 47.5110μs 22.3498μs 44.7430 KOps/s 43.9538 KOps/s $\color{#35bf28}+1.80\%$
test_step_mdp_speed[False-True-True-False-True] 50.1320μs 23.0572μs 43.3703 KOps/s 41.8123 KOps/s $\color{#35bf28}+3.73\%$
test_step_mdp_speed[False-True-True-False-False] 41.9600μs 14.2367μs 70.2410 KOps/s 69.4232 KOps/s $\color{#35bf28}+1.18\%$
test_step_mdp_speed[False-True-False-True-True] 63.8120μs 36.4760μs 27.4153 KOps/s 26.3750 KOps/s $\color{#35bf28}+3.94\%$
test_step_mdp_speed[False-True-False-True-False] 48.6310μs 24.0826μs 41.5238 KOps/s 39.7466 KOps/s $\color{#35bf28}+4.47\%$
test_step_mdp_speed[False-True-False-False-True] 65.0320μs 24.6836μs 40.5127 KOps/s 39.2618 KOps/s $\color{#35bf28}+3.19\%$
test_step_mdp_speed[False-True-False-False-False] 38.8500μs 16.0160μs 62.4375 KOps/s 61.7734 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[False-False-True-True-True] 65.7310μs 37.9869μs 26.3249 KOps/s 25.5627 KOps/s $\color{#35bf28}+2.98\%$
test_step_mdp_speed[False-False-True-True-False] 49.6120μs 25.8449μs 38.6923 KOps/s 37.7499 KOps/s $\color{#35bf28}+2.50\%$
test_step_mdp_speed[False-False-True-False-True] 59.1310μs 24.5637μs 40.7104 KOps/s 38.8729 KOps/s $\color{#35bf28}+4.73\%$
test_step_mdp_speed[False-False-True-False-False] 41.1810μs 15.9726μs 62.6073 KOps/s 61.1566 KOps/s $\color{#35bf28}+2.37\%$
test_step_mdp_speed[False-False-False-True-True] 73.0020μs 39.5480μs 25.2857 KOps/s 24.4327 KOps/s $\color{#35bf28}+3.49\%$
test_step_mdp_speed[False-False-False-True-False] 54.1000μs 27.6557μs 36.1589 KOps/s 35.4184 KOps/s $\color{#35bf28}+2.09\%$
test_step_mdp_speed[False-False-False-False-True] 61.5220μs 26.2353μs 38.1165 KOps/s 36.9170 KOps/s $\color{#35bf28}+3.25\%$
test_step_mdp_speed[False-False-False-False-False] 39.5400μs 17.7627μs 56.2978 KOps/s 55.7666 KOps/s $\color{#35bf28}+0.95\%$
test_values[generalized_advantage_estimate-True-True] 24.3152ms 23.4224ms 42.6942 Ops/s 41.0570 Ops/s $\color{#35bf28}+3.99\%$
test_values[vec_generalized_advantage_estimate-True-True] 84.7684ms 3.2449ms 308.1735 Ops/s 309.2428 Ops/s $\color{#d91a1a}-0.35\%$
test_values[td0_return_estimate-False-False] 98.1620μs 60.2071μs 16.6093 KOps/s 16.9833 KOps/s $\color{#d91a1a}-2.20\%$
test_values[td1_return_estimate-False-False] 50.9076ms 50.1041ms 19.9585 Ops/s 19.2841 Ops/s $\color{#35bf28}+3.50\%$
test_values[vec_td1_return_estimate-False-False] 2.0005ms 1.7360ms 576.0370 Ops/s 571.9111 Ops/s $\color{#35bf28}+0.72\%$
test_values[td_lambda_return_estimate-True-False] 80.9150ms 79.8894ms 12.5173 Ops/s 12.0608 Ops/s $\color{#35bf28}+3.78\%$
test_values[vec_td_lambda_return_estimate-True-False] 4.0943ms 1.7763ms 562.9647 Ops/s 560.0458 Ops/s $\color{#35bf28}+0.52\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 22.3570ms 21.9599ms 45.5376 Ops/s 44.3197 Ops/s $\color{#35bf28}+2.75\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8414ms 0.6764ms 1.4784 KOps/s 1.4695 KOps/s $\color{#35bf28}+0.60\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6828ms 0.6293ms 1.5891 KOps/s 1.5684 KOps/s $\color{#35bf28}+1.32\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5869ms 1.4333ms 697.7073 Ops/s 696.6267 Ops/s $\color{#35bf28}+0.16\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9346ms 0.6437ms 1.5535 KOps/s 1.5210 KOps/s $\color{#35bf28}+2.14\%$
test_dqn_speed 7.9257ms 1.4339ms 697.3960 Ops/s 704.2528 Ops/s $\color{#d91a1a}-0.97\%$
test_ddpg_speed 3.0245ms 2.7246ms 367.0239 Ops/s 366.4580 Ops/s $\color{#35bf28}+0.15\%$
test_sac_speed 8.9322ms 8.4742ms 118.0046 Ops/s 118.7039 Ops/s $\color{#d91a1a}-0.59\%$
test_redq_speed 11.2958ms 10.5897ms 94.4312 Ops/s 93.4889 Ops/s $\color{#35bf28}+1.01\%$
test_redq_deprec_speed 12.0642ms 11.6381ms 85.9250 Ops/s 85.1944 Ops/s $\color{#35bf28}+0.86\%$
test_td3_speed 8.9649ms 8.5481ms 116.9855 Ops/s 117.0989 Ops/s $\color{#d91a1a}-0.10\%$
test_cql_speed 26.2418ms 25.5884ms 39.0802 Ops/s 38.2662 Ops/s $\color{#35bf28}+2.13\%$
test_a2c_speed 5.8320ms 5.5785ms 179.2595 Ops/s 185.8562 Ops/s $\color{#d91a1a}-3.55\%$
test_ppo_speed 6.1026ms 5.9026ms 169.4172 Ops/s 174.7277 Ops/s $\color{#d91a1a}-3.04\%$
test_reinforce_speed 5.2877ms 4.5845ms 218.1269 Ops/s 224.8850 Ops/s $\color{#d91a1a}-3.01\%$
test_iql_speed 0.1144s 21.6644ms 46.1586 Ops/s 49.9158 Ops/s $\textbf{\color{#d91a1a}-7.53\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.6298ms 3.5483ms 281.8239 Ops/s 285.2609 Ops/s $\color{#d91a1a}-1.20\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0804ms 0.5611ms 1.7822 KOps/s 1.7963 KOps/s $\color{#d91a1a}-0.79\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8768ms 0.5350ms 1.8692 KOps/s 1.8792 KOps/s $\color{#d91a1a}-0.53\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8057ms 3.5933ms 278.2994 Ops/s 282.5508 Ops/s $\color{#d91a1a}-1.50\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7462ms 0.5558ms 1.7991 KOps/s 1.8140 KOps/s $\color{#d91a1a}-0.82\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8004ms 0.5320ms 1.8797 KOps/s 1.8989 KOps/s $\color{#d91a1a}-1.01\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.9163ms 3.7040ms 269.9808 Ops/s 275.0567 Ops/s $\color{#d91a1a}-1.85\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8998ms 0.6838ms 1.4625 KOps/s 1.4676 KOps/s $\color{#d91a1a}-0.35\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8473ms 0.6563ms 1.5237 KOps/s 1.5254 KOps/s $\color{#d91a1a}-0.11\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.6860ms 3.5573ms 281.1112 Ops/s 283.4224 Ops/s $\color{#d91a1a}-0.82\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7299ms 0.5628ms 1.7769 KOps/s 1.7855 KOps/s $\color{#d91a1a}-0.49\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6604ms 0.5355ms 1.8674 KOps/s 1.8606 KOps/s $\color{#35bf28}+0.37\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8487ms 3.5891ms 278.6177 Ops/s 280.8281 Ops/s $\color{#d91a1a}-0.79\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7987ms 0.5590ms 1.7889 KOps/s 1.8067 KOps/s $\color{#d91a1a}-0.99\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8008ms 0.5332ms 1.8754 KOps/s 1.8971 KOps/s $\color{#d91a1a}-1.14\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.7951ms 3.7051ms 269.9002 Ops/s 273.2757 Ops/s $\color{#d91a1a}-1.24\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8289ms 0.6910ms 1.4471 KOps/s 1.4595 KOps/s $\color{#d91a1a}-0.85\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8758ms 0.6684ms 1.4960 KOps/s 1.5156 KOps/s $\color{#d91a1a}-1.29\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1402s 10.4942ms 95.2906 Ops/s 98.7034 Ops/s $\color{#d91a1a}-3.46\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 17.6446ms 15.6285ms 63.9856 Ops/s 55.7319 Ops/s $\textbf{\color{#35bf28}+14.81\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.0343ms 3.0467ms 328.2285 Ops/s 326.7982 Ops/s $\color{#35bf28}+0.44\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1208s 9.9607ms 100.3941 Ops/s 99.4703 Ops/s $\color{#35bf28}+0.93\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.6005ms 15.5720ms 64.2180 Ops/s 63.7587 Ops/s $\color{#35bf28}+0.72\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.9089ms 3.0461ms 328.2866 Ops/s 324.5979 Ops/s $\color{#35bf28}+1.14\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1206s 10.2473ms 97.5864 Ops/s 97.5004 Ops/s $\color{#35bf28}+0.09\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.1735ms 15.7806ms 63.3689 Ops/s 63.1159 Ops/s $\color{#35bf28}+0.40\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 8.2599ms 3.3958ms 294.4809 Ops/s 295.7223 Ops/s $\color{#d91a1a}-0.42\%$

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working Suitable for minor Suitable to be integrated in minor release (no new feature)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants