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

[Feature] Allow non-sorted keys in CatFrames #1913

Merged
merged 1 commit into from
Feb 15, 2024
Merged

[Feature] Allow non-sorted keys in CatFrames #1913

merged 1 commit into from
Feb 15, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 15, 2024 •
edited
Loading

cc @teopir

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Feb 15, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1913

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

✅ You can merge normally! (3 Unrelated Failures)

As of commit f8ba8b5 with merge base 45764b5 (image):

FLAKY - The following job failed but was likely due to flakiness present on trunk:

BROKEN TRUNK - The following jobs failed but was 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 15, 2024
@vmoens vmoens added the enhancement New feature or request label Feb 15, 2024
@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1374s 67.6863ms 14.7740 Ops/s 15.0752 Ops/s $\color{#d91a1a}-2.00\%$
test_sync 37.4647ms 34.5421ms 28.9502 Ops/s 28.8575 Ops/s $\color{#35bf28}+0.32\%$
test_async 0.1390s 34.0481ms 29.3702 Ops/s 29.9193 Ops/s $\color{#d91a1a}-1.84\%$
test_simple 0.4969s 0.4360s 2.2935 Ops/s 2.2316 Ops/s $\color{#35bf28}+2.77\%$
test_transformed 0.6509s 0.5954s 1.6795 Ops/s 1.6168 Ops/s $\color{#35bf28}+3.88\%$
test_serial 1.4656s 1.4123s 0.7080 Ops/s 0.6783 Ops/s $\color{#35bf28}+4.39\%$
test_parallel 1.4308s 1.3669s 0.7316 Ops/s 0.7031 Ops/s $\color{#35bf28}+4.04\%$
test_step_mdp_speed[True-True-True-True-True] 0.1804ms 21.3704μs 46.7936 KOps/s 46.6030 KOps/s $\color{#35bf28}+0.41\%$
test_step_mdp_speed[True-True-True-True-False] 43.7120μs 12.9798μs 77.0426 KOps/s 75.9307 KOps/s $\color{#35bf28}+1.46\%$
test_step_mdp_speed[True-True-True-False-True] 63.3600μs 12.6672μs 78.9440 KOps/s 79.3715 KOps/s $\color{#d91a1a}-0.54\%$
test_step_mdp_speed[True-True-True-False-False] 35.9180μs 7.5592μs 132.2898 KOps/s 129.5671 KOps/s $\color{#35bf28}+2.10\%$
test_step_mdp_speed[True-True-False-True-True] 55.8650μs 22.8346μs 43.7932 KOps/s 44.2142 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[True-True-False-True-False] 47.5200μs 14.2311μs 70.2685 KOps/s 69.6614 KOps/s $\color{#35bf28}+0.87\%$
test_step_mdp_speed[True-True-False-False-True] 55.8550μs 13.7993μs 72.4674 KOps/s 72.1484 KOps/s $\color{#35bf28}+0.44\%$
test_step_mdp_speed[True-True-False-False-False] 41.3280μs 8.8785μs 112.6320 KOps/s 111.8013 KOps/s $\color{#35bf28}+0.74\%$
test_step_mdp_speed[True-False-True-True-True] 55.9850μs 24.4120μs 40.9634 KOps/s 41.1263 KOps/s $\color{#d91a1a}-0.40\%$
test_step_mdp_speed[True-False-True-True-False] 40.3560μs 15.6996μs 63.6960 KOps/s 63.6060 KOps/s $\color{#35bf28}+0.14\%$
test_step_mdp_speed[True-False-True-False-True] 54.8240μs 13.7733μs 72.6042 KOps/s 72.3666 KOps/s $\color{#35bf28}+0.33\%$
test_step_mdp_speed[True-False-True-False-False] 34.0040μs 8.7680μs 114.0514 KOps/s 111.6797 KOps/s $\color{#35bf28}+2.12\%$
test_step_mdp_speed[True-False-False-True-True] 60.6640μs 25.2179μs 39.6543 KOps/s 39.4582 KOps/s $\color{#35bf28}+0.50\%$
test_step_mdp_speed[True-False-False-True-False] 58.3100μs 16.7965μs 59.5362 KOps/s 58.6532 KOps/s $\color{#35bf28}+1.51\%$
test_step_mdp_speed[True-False-False-False-True] 52.3390μs 14.8989μs 67.1191 KOps/s 66.6076 KOps/s $\color{#35bf28}+0.77\%$
test_step_mdp_speed[True-False-False-False-False] 44.0030μs 10.0742μs 99.2631 KOps/s 98.1615 KOps/s $\color{#35bf28}+1.12\%$
test_step_mdp_speed[False-True-True-True-True] 66.5650μs 24.2962μs 41.1587 KOps/s 41.7241 KOps/s $\color{#d91a1a}-1.35\%$
test_step_mdp_speed[False-True-True-True-False] 52.4690μs 15.7605μs 63.4497 KOps/s 63.3126 KOps/s $\color{#35bf28}+0.22\%$
test_step_mdp_speed[False-True-True-False-True] 46.6270μs 16.0590μs 62.2704 KOps/s 61.7723 KOps/s $\color{#35bf28}+0.81\%$
test_step_mdp_speed[False-True-True-False-False] 36.5080μs 10.1401μs 98.6182 KOps/s 97.6707 KOps/s $\color{#35bf28}+0.97\%$
test_step_mdp_speed[False-True-False-True-True] 91.0920μs 26.0136μs 38.4414 KOps/s 38.7403 KOps/s $\color{#d91a1a}-0.77\%$
test_step_mdp_speed[False-True-False-True-False] 54.0110μs 16.8158μs 59.4678 KOps/s 58.6959 KOps/s $\color{#35bf28}+1.32\%$
test_step_mdp_speed[False-True-False-False-True] 60.1240μs 17.1018μs 58.4733 KOps/s 57.7086 KOps/s $\color{#35bf28}+1.33\%$
test_step_mdp_speed[False-True-False-False-False] 50.7960μs 11.3497μs 88.1083 KOps/s 87.6613 KOps/s $\color{#35bf28}+0.51\%$
test_step_mdp_speed[False-False-True-True-True] 62.1570μs 26.7379μs 37.4000 KOps/s 37.5148 KOps/s $\color{#d91a1a}-0.31\%$
test_step_mdp_speed[False-False-True-True-False] 69.0300μs 18.0417μs 55.4272 KOps/s 54.2053 KOps/s $\color{#35bf28}+2.25\%$
test_step_mdp_speed[False-False-True-False-True] 49.1020μs 17.1267μs 58.3884 KOps/s 58.0055 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[False-False-True-False-False] 40.4860μs 11.2542μs 88.8555 KOps/s 87.7276 KOps/s $\color{#35bf28}+1.29\%$
test_step_mdp_speed[False-False-False-True-True] 66.0640μs 27.6133μs 36.2145 KOps/s 36.0449 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[False-False-False-True-False] 51.1060μs 19.0623μs 52.4595 KOps/s 51.3611 KOps/s $\color{#35bf28}+2.14\%$
test_step_mdp_speed[False-False-False-False-True] 53.9020μs 18.1913μs 54.9713 KOps/s 54.5861 KOps/s $\color{#35bf28}+0.71\%$
test_step_mdp_speed[False-False-False-False-False] 48.0200μs 12.3397μs 81.0389 KOps/s 80.1223 KOps/s $\color{#35bf28}+1.14\%$
test_values[generalized_advantage_estimate-True-True] 10.2998ms 9.5743ms 104.4464 Ops/s 103.7990 Ops/s $\color{#35bf28}+0.62\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.5695ms 33.4158ms 29.9259 Ops/s 29.5530 Ops/s $\color{#35bf28}+1.26\%$
test_values[td0_return_estimate-False-False] 0.2729ms 0.1920ms 5.2075 KOps/s 5.5687 KOps/s $\textbf{\color{#d91a1a}-6.49\%}$
test_values[td1_return_estimate-False-False] 25.0998ms 23.7838ms 42.0454 Ops/s 42.8152 Ops/s $\color{#d91a1a}-1.80\%$
test_values[vec_td1_return_estimate-False-False] 35.7569ms 33.7606ms 29.6203 Ops/s 29.7951 Ops/s $\color{#d91a1a}-0.59\%$
test_values[td_lambda_return_estimate-True-False] 38.5308ms 34.4343ms 29.0408 Ops/s 28.9702 Ops/s $\color{#35bf28}+0.24\%$
test_values[vec_td_lambda_return_estimate-True-False] 34.9340ms 33.6145ms 29.7490 Ops/s 29.6846 Ops/s $\color{#35bf28}+0.22\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.3737ms 8.1704ms 122.3935 Ops/s 121.6455 Ops/s $\color{#35bf28}+0.61\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.9948ms 1.7926ms 557.8613 Ops/s 497.2768 Ops/s $\textbf{\color{#35bf28}+12.18\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5514ms 0.3501ms 2.8561 KOps/s 2.7705 KOps/s $\color{#35bf28}+3.09\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 42.8859ms 41.4920ms 24.1010 Ops/s 21.8830 Ops/s $\textbf{\color{#35bf28}+10.14\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8660ms 3.0562ms 327.2058 Ops/s 328.7971 Ops/s $\color{#d91a1a}-0.48\%$
test_dqn_speed 84.3978ms 1.5157ms 659.7509 Ops/s 702.7298 Ops/s $\textbf{\color{#d91a1a}-6.12\%}$
test_ddpg_speed 3.2965ms 2.7606ms 362.2350 Ops/s 356.5632 Ops/s $\color{#35bf28}+1.59\%$
test_sac_speed 10.8881ms 8.7468ms 114.3280 Ops/s 112.3441 Ops/s $\color{#35bf28}+1.77\%$
test_redq_speed 14.9582ms 13.7822ms 72.5573 Ops/s 70.0669 Ops/s $\color{#35bf28}+3.55\%$
test_redq_deprec_speed 15.9756ms 14.3314ms 69.7769 Ops/s 68.3068 Ops/s $\color{#35bf28}+2.15\%$
test_td3_speed 11.0480ms 8.7544ms 114.2277 Ops/s 107.9418 Ops/s $\textbf{\color{#35bf28}+5.82\%}$
test_cql_speed 39.5062ms 37.0822ms 26.9671 Ops/s 26.4179 Ops/s $\color{#35bf28}+2.08\%$
test_a2c_speed 12.4654ms 7.4632ms 133.9914 Ops/s 130.1218 Ops/s $\color{#35bf28}+2.97\%$
test_ppo_speed 10.9673ms 8.0793ms 123.7724 Ops/s 120.2648 Ops/s $\color{#35bf28}+2.92\%$
test_reinforce_speed 8.9278ms 6.8018ms 147.0202 Ops/s 145.5369 Ops/s $\color{#35bf28}+1.02\%$
test_iql_speed 34.8568ms 33.2335ms 30.0901 Ops/s 29.2052 Ops/s $\color{#35bf28}+3.03\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.3868ms 2.8703ms 348.3977 Ops/s 334.9668 Ops/s $\color{#35bf28}+4.01\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8671ms 0.5247ms 1.9057 KOps/s 1.8571 KOps/s $\color{#35bf28}+2.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7169ms 0.4923ms 2.0311 KOps/s 1.9601 KOps/s $\color{#35bf28}+3.62\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.5133ms 2.9116ms 343.4492 Ops/s 315.2291 Ops/s $\textbf{\color{#35bf28}+8.95\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7870ms 0.5195ms 1.9249 KOps/s 1.8844 KOps/s $\color{#35bf28}+2.15\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6140ms 0.4907ms 2.0377 KOps/s 1.9942 KOps/s $\color{#35bf28}+2.18\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.7554ms 3.1360ms 318.8794 Ops/s 324.0067 Ops/s $\color{#d91a1a}-1.58\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0465ms 0.6427ms 1.5558 KOps/s 1.5104 KOps/s $\color{#35bf28}+3.01\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9937ms 0.6142ms 1.6280 KOps/s 1.5894 KOps/s $\color{#35bf28}+2.43\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.9127ms 3.1375ms 318.7261 Ops/s 348.8757 Ops/s $\textbf{\color{#d91a1a}-8.64\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6315ms 0.5201ms 1.9227 KOps/s 1.8755 KOps/s $\color{#35bf28}+2.52\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9070ms 0.5030ms 1.9881 KOps/s 1.9487 KOps/s $\color{#35bf28}+2.03\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.8447ms 3.0672ms 326.0338 Ops/s 330.8440 Ops/s $\color{#d91a1a}-1.45\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6492ms 0.5247ms 1.9059 KOps/s 1.9371 KOps/s $\color{#d91a1a}-1.61\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8045ms 0.5022ms 1.9911 KOps/s 1.9468 KOps/s $\color{#35bf28}+2.28\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.3189ms 3.3174ms 301.4451 Ops/s 294.9598 Ops/s $\color{#35bf28}+2.20\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9405ms 0.6598ms 1.5157 KOps/s 1.2686 KOps/s $\textbf{\color{#35bf28}+19.48\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7218ms 0.6090ms 1.6419 KOps/s 1.5865 KOps/s $\color{#35bf28}+3.49\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1474s 9.3099ms 107.4123 Ops/s 120.2126 Ops/s $\textbf{\color{#d91a1a}-10.65\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 15.4579ms 13.0641ms 76.5454 Ops/s 74.2732 Ops/s $\color{#35bf28}+3.06\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 4.8832ms 2.5374ms 394.1044 Ops/s 383.5691 Ops/s $\color{#35bf28}+2.75\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1129s 10.5957ms 94.3783 Ops/s 91.8330 Ops/s $\color{#35bf28}+2.77\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.0233ms 13.5182ms 73.9743 Ops/s 74.2304 Ops/s $\color{#d91a1a}-0.35\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.1085ms 2.5811ms 387.4380 Ops/s 390.4508 Ops/s $\color{#d91a1a}-0.77\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1112s 8.5750ms 116.6185 Ops/s 118.1852 Ops/s $\color{#d91a1a}-1.33\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 16.5625ms 13.7284ms 72.8416 Ops/s 70.0259 Ops/s $\color{#35bf28}+4.02\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.2803ms 2.8153ms 355.2058 Ops/s 353.5571 Ops/s $\color{#35bf28}+0.47\%$

@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1162s 0.1158s 8.6356 Ops/s 8.8371 Ops/s $\color{#d91a1a}-2.28\%$
test_sync 0.1713s 0.1022s 9.7810 Ops/s 9.6460 Ops/s $\color{#35bf28}+1.40\%$
test_async 0.2543s 92.1241ms 10.8549 Ops/s 10.8556 Ops/s $-0.01\%$
test_single_pixels 0.1388s 0.1331s 7.5114 Ops/s 7.9301 Ops/s $\textbf{\color{#d91a1a}-5.28\%}$
test_sync_pixels 81.1031ms 79.2254ms 12.6222 Ops/s 12.6703 Ops/s $\color{#d91a1a}-0.38\%$
test_async_pixels 0.2094s 74.6100ms 13.4030 Ops/s 13.2956 Ops/s $\color{#35bf28}+0.81\%$
test_simple 0.8998s 0.8313s 1.2030 Ops/s 1.2641 Ops/s $\color{#d91a1a}-4.84\%$
test_transformed 1.1384s 1.0753s 0.9300 Ops/s 0.9527 Ops/s $\color{#d91a1a}-2.38\%$
test_serial 2.4734s 2.4067s 0.4155 Ops/s 0.4320 Ops/s $\color{#d91a1a}-3.82\%$
test_parallel 2.2152s 2.1099s 0.4739 Ops/s 0.4827 Ops/s $\color{#d91a1a}-1.82\%$
test_step_mdp_speed[True-True-True-True-True] 0.1041ms 33.8297μs 29.5598 KOps/s 30.3033 KOps/s $\color{#d91a1a}-2.45\%$
test_step_mdp_speed[True-True-True-True-False] 44.0610μs 19.9638μs 50.0907 KOps/s 51.1853 KOps/s $\color{#d91a1a}-2.14\%$
test_step_mdp_speed[True-True-True-False-True] 35.8700μs 19.0513μs 52.4899 KOps/s 54.2003 KOps/s $\color{#d91a1a}-3.16\%$
test_step_mdp_speed[True-True-True-False-False] 27.9600μs 11.2907μs 88.5687 KOps/s 90.8494 KOps/s $\color{#d91a1a}-2.51\%$
test_step_mdp_speed[True-True-False-True-True] 77.7710μs 35.5172μs 28.1554 KOps/s 28.7879 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[True-True-False-True-False] 46.1210μs 22.1390μs 45.1691 KOps/s 47.0114 KOps/s $\color{#d91a1a}-3.92\%$
test_step_mdp_speed[True-True-False-False-True] 45.7800μs 20.9672μs 47.6935 KOps/s 49.4770 KOps/s $\color{#d91a1a}-3.60\%$
test_step_mdp_speed[True-True-False-False-False] 36.0500μs 13.1770μs 75.8899 KOps/s 76.7162 KOps/s $\color{#d91a1a}-1.08\%$
test_step_mdp_speed[True-False-True-True-True] 57.7800μs 37.3016μs 26.8085 KOps/s 26.8624 KOps/s $\color{#d91a1a}-0.20\%$
test_step_mdp_speed[True-False-True-True-False] 46.9020μs 23.8636μs 41.9047 KOps/s 42.8731 KOps/s $\color{#d91a1a}-2.26\%$
test_step_mdp_speed[True-False-True-False-True] 41.6910μs 20.6551μs 48.4143 KOps/s 48.5380 KOps/s $\color{#d91a1a}-0.25\%$
test_step_mdp_speed[True-False-True-False-False] 36.8410μs 13.2086μs 75.7084 KOps/s 78.2077 KOps/s $\color{#d91a1a}-3.20\%$
test_step_mdp_speed[True-False-False-True-True] 60.8110μs 39.7493μs 25.1577 KOps/s 26.5851 KOps/s $\textbf{\color{#d91a1a}-5.37\%}$
test_step_mdp_speed[True-False-False-True-False] 43.1810μs 25.8786μs 38.6419 KOps/s 40.8363 KOps/s $\textbf{\color{#d91a1a}-5.37\%}$
test_step_mdp_speed[True-False-False-False-True] 48.5010μs 22.9780μs 43.5199 KOps/s 45.2705 KOps/s $\color{#d91a1a}-3.87\%$
test_step_mdp_speed[True-False-False-False-False] 38.7910μs 15.1015μs 66.2184 KOps/s 68.1770 KOps/s $\color{#d91a1a}-2.87\%$
test_step_mdp_speed[False-True-True-True-True] 58.3110μs 37.5381μs 26.6396 KOps/s 27.5022 KOps/s $\color{#d91a1a}-3.14\%$
test_step_mdp_speed[False-True-True-True-False] 38.9020μs 23.8323μs 41.9599 KOps/s 43.5461 KOps/s $\color{#d91a1a}-3.64\%$
test_step_mdp_speed[False-True-True-False-True] 46.8010μs 24.6473μs 40.5724 KOps/s 40.7410 KOps/s $\color{#d91a1a}-0.41\%$
test_step_mdp_speed[False-True-True-False-False] 49.4800μs 15.0681μs 66.3655 KOps/s 68.0296 KOps/s $\color{#d91a1a}-2.45\%$
test_step_mdp_speed[False-True-False-True-True] 60.2310μs 39.7564μs 25.1532 KOps/s 26.0252 KOps/s $\color{#d91a1a}-3.35\%$
test_step_mdp_speed[False-True-False-True-False] 52.6010μs 25.6661μs 38.9620 KOps/s 39.8072 KOps/s $\color{#d91a1a}-2.12\%$
test_step_mdp_speed[False-True-False-False-True] 42.7000μs 26.5017μs 37.7334 KOps/s 37.7284 KOps/s $\color{#35bf28}+0.01\%$
test_step_mdp_speed[False-True-False-False-False] 38.5110μs 17.1235μs 58.3992 KOps/s 61.3530 KOps/s $\color{#d91a1a}-4.81\%$
test_step_mdp_speed[False-False-True-True-True] 62.6400μs 41.3521μs 24.1826 KOps/s 25.3710 KOps/s $\color{#d91a1a}-4.68\%$
test_step_mdp_speed[False-False-True-True-False] 46.2410μs 27.7844μs 35.9914 KOps/s 37.5470 KOps/s $\color{#d91a1a}-4.14\%$
test_step_mdp_speed[False-False-True-False-True] 48.8400μs 25.8254μs 38.7216 KOps/s 37.8396 KOps/s $\color{#35bf28}+2.33\%$
test_step_mdp_speed[False-False-True-False-False] 33.4210μs 16.8239μs 59.4391 KOps/s 61.2562 KOps/s $\color{#d91a1a}-2.97\%$
test_step_mdp_speed[False-False-False-True-True] 66.8010μs 42.7637μs 23.3843 KOps/s 24.5254 KOps/s $\color{#d91a1a}-4.65\%$
test_step_mdp_speed[False-False-False-True-False] 72.4810μs 29.2733μs 34.1608 KOps/s 34.4884 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[False-False-False-False-True] 51.2610μs 27.7557μs 36.0286 KOps/s 35.9037 KOps/s $\color{#35bf28}+0.35\%$
test_step_mdp_speed[False-False-False-False-False] 52.4410μs 18.6382μs 53.6532 KOps/s 54.7656 KOps/s $\color{#d91a1a}-2.03\%$
test_values[generalized_advantage_estimate-True-True] 25.7909ms 25.4354ms 39.3154 Ops/s 41.9611 Ops/s $\textbf{\color{#d91a1a}-6.31\%}$
test_values[vec_generalized_advantage_estimate-True-True] 83.3897ms 3.2268ms 309.9087 Ops/s 315.0055 Ops/s $\color{#d91a1a}-1.62\%$
test_values[td0_return_estimate-False-False] 0.1040ms 64.5837μs 15.4838 KOps/s 16.4578 KOps/s $\textbf{\color{#d91a1a}-5.92\%}$
test_values[td1_return_estimate-False-False] 54.7295ms 54.2259ms 18.4414 Ops/s 19.6003 Ops/s $\textbf{\color{#d91a1a}-5.91\%}$
test_values[vec_td1_return_estimate-False-False] 2.1073ms 1.7750ms 563.3901 Ops/s 574.4561 Ops/s $\color{#d91a1a}-1.93\%$
test_values[td_lambda_return_estimate-True-False] 87.6246ms 85.2103ms 11.7357 Ops/s 12.3000 Ops/s $\color{#d91a1a}-4.59\%$
test_values[vec_td_lambda_return_estimate-True-False] 4.1637ms 1.7915ms 558.1760 Ops/s 560.2707 Ops/s $\color{#d91a1a}-0.37\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.0974ms 22.8847ms 43.6974 Ops/s 45.0309 Ops/s $\color{#d91a1a}-2.96\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8984ms 0.7194ms 1.3901 KOps/s 1.4793 KOps/s $\textbf{\color{#d91a1a}-6.03\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7224ms 0.6494ms 1.5399 KOps/s 1.5688 KOps/s $\color{#d91a1a}-1.84\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5034ms 1.4511ms 689.1171 Ops/s 694.6835 Ops/s $\color{#d91a1a}-0.80\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9496ms 0.6685ms 1.4960 KOps/s 1.5194 KOps/s $\color{#d91a1a}-1.54\%$
test_dqn_speed 1.8764ms 1.4400ms 694.4600 Ops/s 714.0784 Ops/s $\color{#d91a1a}-2.75\%$
test_ddpg_speed 3.1813ms 2.7486ms 363.8155 Ops/s 373.8879 Ops/s $\color{#d91a1a}-2.69\%$
test_sac_speed 8.8565ms 8.4750ms 117.9935 Ops/s 121.6645 Ops/s $\color{#d91a1a}-3.02\%$
test_redq_speed 11.4299ms 10.6305ms 94.0685 Ops/s 97.9092 Ops/s $\color{#d91a1a}-3.92\%$
test_redq_deprec_speed 12.4211ms 11.6139ms 86.1038 Ops/s 88.6436 Ops/s $\color{#d91a1a}-2.87\%$
test_td3_speed 8.7530ms 8.6161ms 116.0619 Ops/s 117.8301 Ops/s $\color{#d91a1a}-1.50\%$
test_cql_speed 0.1191s 28.0456ms 35.6562 Ops/s 39.4862 Ops/s $\textbf{\color{#d91a1a}-9.70\%}$
test_a2c_speed 5.5981ms 5.3763ms 186.0000 Ops/s 187.4558 Ops/s $\color{#d91a1a}-0.78\%$
test_ppo_speed 6.2702ms 5.6739ms 176.2449 Ops/s 176.4022 Ops/s $\color{#d91a1a}-0.09\%$
test_reinforce_speed 5.1805ms 4.4212ms 226.1817 Ops/s 226.1265 Ops/s $\color{#35bf28}+0.02\%$
test_iql_speed 20.3756ms 19.7570ms 50.6150 Ops/s 50.4455 Ops/s $\color{#35bf28}+0.34\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.7040ms 3.5646ms 280.5396 Ops/s 289.7358 Ops/s $\color{#d91a1a}-3.17\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8289ms 0.5585ms 1.7904 KOps/s 1.8086 KOps/s $\color{#d91a1a}-1.00\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6563ms 0.5316ms 1.8810 KOps/s 1.8925 KOps/s $\color{#d91a1a}-0.60\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.0670ms 3.6071ms 277.2276 Ops/s 284.1352 Ops/s $\color{#d91a1a}-2.43\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7167ms 0.5555ms 1.8001 KOps/s 1.8332 KOps/s $\color{#d91a1a}-1.81\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6675ms 0.5230ms 1.9121 KOps/s 1.9176 KOps/s $\color{#d91a1a}-0.29\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.8218ms 3.6908ms 270.9416 Ops/s 276.5962 Ops/s $\color{#d91a1a}-2.04\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8912ms 0.6779ms 1.4752 KOps/s 1.4824 KOps/s $\color{#d91a1a}-0.48\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8791ms 0.6518ms 1.5342 KOps/s 1.5345 KOps/s $\color{#d91a1a}-0.02\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.9469ms 3.5799ms 279.3410 Ops/s 287.2009 Ops/s $\color{#d91a1a}-2.74\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6746ms 0.5581ms 1.7917 KOps/s 1.8149 KOps/s $\color{#d91a1a}-1.28\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7373ms 0.5355ms 1.8674 KOps/s 1.8999 KOps/s $\color{#d91a1a}-1.71\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8220ms 3.5775ms 279.5271 Ops/s 285.2037 Ops/s $\color{#d91a1a}-1.99\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6600ms 0.5534ms 1.8070 KOps/s 1.8257 KOps/s $\color{#d91a1a}-1.02\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7865ms 0.5302ms 1.8861 KOps/s 1.9156 KOps/s $\color{#d91a1a}-1.54\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.8097ms 3.6761ms 272.0266 Ops/s 274.1894 Ops/s $\color{#d91a1a}-0.79\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9556ms 0.6883ms 1.4528 KOps/s 1.4762 KOps/s $\color{#d91a1a}-1.59\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7942ms 0.6558ms 1.5248 KOps/s 1.5409 KOps/s $\color{#d91a1a}-1.04\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1362s 10.3598ms 96.5270 Ops/s 97.8987 Ops/s $\color{#d91a1a}-1.40\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 18.2655ms 16.2442ms 61.5603 Ops/s 64.2441 Ops/s $\color{#d91a1a}-4.18\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.1080ms 3.0617ms 326.6164 Ops/s 330.4131 Ops/s $\color{#d91a1a}-1.15\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1172s 9.9737ms 100.2635 Ops/s 99.8572 Ops/s $\color{#35bf28}+0.41\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 18.6506ms 16.2791ms 61.4285 Ops/s 63.7985 Ops/s $\color{#d91a1a}-3.71\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.4974ms 3.0672ms 326.0295 Ops/s 330.7347 Ops/s $\color{#d91a1a}-1.42\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1220s 10.3532ms 96.5887 Ops/s 79.9538 Ops/s $\textbf{\color{#35bf28}+20.81\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1256s 18.5923ms 53.7858 Ops/s 63.8356 Ops/s $\textbf{\color{#d91a1a}-15.74\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.7875ms 3.3044ms 302.6273 Ops/s 298.4698 Ops/s $\color{#35bf28}+1.39\%$

@vmoens vmoens merged commit 57ac22b into main Feb 15, 2024
64 of 67 checks passed
@vmoens vmoens deleted the non-sorted-cat branch February 15, 2024 15:33
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. enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

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