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 slicesampler terminated/truncated signaling #2044

Merged
merged 2 commits into from
Mar 27, 2024
Merged

[BugFix] Fix slicesampler terminated/truncated signaling #2044

merged 2 commits into from
Mar 27, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Mar 27, 2024 •
edited
Loading

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Mar 27, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2044

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

❌ 3 New Failures, 1 Unrelated Failure

As of commit c15f41a with merge base f439b54 (image):

NEW FAILURES - The following jobs have failed:

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 Mar 27, 2024
@vmoens vmoens added the bug Something isn't working label Mar 27, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 27, 2024 •
edited
Loading

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}39$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 52.0931ms 51.6284ms 19.3692 Ops/s 17.7617 Ops/s $\textbf{\color{#35bf28}+9.05\%}$
test_sync 29.0482ms 28.6328ms 34.9249 Ops/s 31.2920 Ops/s $\textbf{\color{#35bf28}+11.61\%}$
test_async 52.1231ms 26.6079ms 37.5828 Ops/s 35.2182 Ops/s $\textbf{\color{#35bf28}+6.71\%}$
test_simple 0.3235s 0.3211s 3.1138 Ops/s 2.7645 Ops/s $\textbf{\color{#35bf28}+12.64\%}$
test_transformed 0.5368s 0.4784s 2.0904 Ops/s 1.9867 Ops/s $\textbf{\color{#35bf28}+5.22\%}$
test_serial 1.2519s 1.1880s 0.8418 Ops/s 0.8133 Ops/s $\color{#35bf28}+3.50\%$
test_parallel 1.0664s 1.0008s 0.9992 Ops/s 0.9730 Ops/s $\color{#35bf28}+2.69\%$
test_step_mdp_speed[True-True-True-True-True] 0.1470ms 21.1713μs 47.2337 KOps/s 44.7823 KOps/s $\textbf{\color{#35bf28}+5.47\%}$
test_step_mdp_speed[True-True-True-True-False] 35.8670μs 12.8995μs 77.5224 KOps/s 72.5021 KOps/s $\textbf{\color{#35bf28}+6.92\%}$
test_step_mdp_speed[True-True-True-False-True] 36.2980μs 12.5387μs 79.7532 KOps/s 76.0915 KOps/s $\color{#35bf28}+4.81\%$
test_step_mdp_speed[True-True-True-False-False] 53.8610μs 7.5806μs 131.9161 KOps/s 126.2291 KOps/s $\color{#35bf28}+4.51\%$
test_step_mdp_speed[True-True-False-True-True] 58.6990μs 22.3783μs 44.6861 KOps/s 41.5950 KOps/s $\textbf{\color{#35bf28}+7.43\%}$
test_step_mdp_speed[True-True-False-True-False] 37.0390μs 14.2295μs 70.2765 KOps/s 66.0323 KOps/s $\textbf{\color{#35bf28}+6.43\%}$
test_step_mdp_speed[True-True-False-False-True] 74.1380μs 13.7356μs 72.8037 KOps/s 68.8982 KOps/s $\textbf{\color{#35bf28}+5.67\%}$
test_step_mdp_speed[True-True-False-False-False] 34.0340μs 8.8025μs 113.6043 KOps/s 107.5955 KOps/s $\textbf{\color{#35bf28}+5.58\%}$
test_step_mdp_speed[True-False-True-True-True] 47.9590μs 23.8165μs 41.9878 KOps/s 38.9996 KOps/s $\textbf{\color{#35bf28}+7.66\%}$
test_step_mdp_speed[True-False-True-True-False] 44.2330μs 15.5195μs 64.4351 KOps/s 59.5362 KOps/s $\textbf{\color{#35bf28}+8.23\%}$
test_step_mdp_speed[True-False-True-False-True] 39.0020μs 13.6685μs 73.1607 KOps/s 69.2535 KOps/s $\textbf{\color{#35bf28}+5.64\%}$
test_step_mdp_speed[True-False-True-False-False] 39.1530μs 8.7798μs 113.8975 KOps/s 107.3053 KOps/s $\textbf{\color{#35bf28}+6.14\%}$
test_step_mdp_speed[True-False-False-True-True] 59.1800μs 25.0489μs 39.9220 KOps/s 36.9533 KOps/s $\textbf{\color{#35bf28}+8.03\%}$
test_step_mdp_speed[True-False-False-True-False] 45.8860μs 16.5490μs 60.4267 KOps/s 55.0205 KOps/s $\textbf{\color{#35bf28}+9.83\%}$
test_step_mdp_speed[True-False-False-False-True] 39.4140μs 14.6463μs 68.2765 KOps/s 63.2028 KOps/s $\textbf{\color{#35bf28}+8.03\%}$
test_step_mdp_speed[True-False-False-False-False] 33.3820μs 10.0020μs 99.9804 KOps/s 94.1757 KOps/s $\textbf{\color{#35bf28}+6.16\%}$
test_step_mdp_speed[False-True-True-True-True] 56.5450μs 23.8132μs 41.9934 KOps/s 39.0555 KOps/s $\textbf{\color{#35bf28}+7.52\%}$
test_step_mdp_speed[False-True-True-True-False] 35.4660μs 15.5811μs 64.1803 KOps/s 60.5390 KOps/s $\textbf{\color{#35bf28}+6.01\%}$
test_step_mdp_speed[False-True-True-False-True] 59.3000μs 15.8212μs 63.2065 KOps/s 59.5876 KOps/s $\textbf{\color{#35bf28}+6.07\%}$
test_step_mdp_speed[False-True-True-False-False] 25.1870μs 10.1578μs 98.4469 KOps/s 95.5420 KOps/s $\color{#35bf28}+3.04\%$
test_step_mdp_speed[False-True-False-True-True] 35.9070μs 25.0148μs 39.9763 KOps/s 36.1107 KOps/s $\textbf{\color{#35bf28}+10.70\%}$
test_step_mdp_speed[False-True-False-True-False] 52.7990μs 16.7859μs 59.5737 KOps/s 55.5450 KOps/s $\textbf{\color{#35bf28}+7.25\%}$
test_step_mdp_speed[False-True-False-False-True] 37.2890μs 17.0015μs 58.8184 KOps/s 55.1644 KOps/s $\textbf{\color{#35bf28}+6.62\%}$
test_step_mdp_speed[False-True-False-False-False] 30.1260μs 11.2121μs 89.1895 KOps/s 83.8951 KOps/s $\textbf{\color{#35bf28}+6.31\%}$
test_step_mdp_speed[False-False-True-True-True] 64.8310μs 26.1905μs 38.1817 KOps/s 35.6987 KOps/s $\textbf{\color{#35bf28}+6.96\%}$
test_step_mdp_speed[False-False-True-True-False] 50.3140μs 18.0823μs 55.3027 KOps/s 51.5582 KOps/s $\textbf{\color{#35bf28}+7.26\%}$
test_step_mdp_speed[False-False-True-False-True] 40.2250μs 17.0032μs 58.8123 KOps/s 55.8014 KOps/s $\textbf{\color{#35bf28}+5.40\%}$
test_step_mdp_speed[False-False-True-False-False] 34.4640μs 11.2783μs 88.6656 KOps/s 83.8115 KOps/s $\textbf{\color{#35bf28}+5.79\%}$
test_step_mdp_speed[False-False-False-True-True] 58.0080μs 27.2083μs 36.7534 KOps/s 34.2698 KOps/s $\textbf{\color{#35bf28}+7.25\%}$
test_step_mdp_speed[False-False-False-True-False] 42.1990μs 19.1716μs 52.1604 KOps/s 48.4091 KOps/s $\textbf{\color{#35bf28}+7.75\%}$
test_step_mdp_speed[False-False-False-False-True] 49.3120μs 17.7900μs 56.2113 KOps/s 52.0400 KOps/s $\textbf{\color{#35bf28}+8.02\%}$
test_step_mdp_speed[False-False-False-False-False] 37.0590μs 12.2999μs 81.3015 KOps/s 75.9526 KOps/s $\textbf{\color{#35bf28}+7.04\%}$
test_values[generalized_advantage_estimate-True-True] 10.5295ms 9.0759ms 110.1822 Ops/s 108.4944 Ops/s $\color{#35bf28}+1.56\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.6922ms 35.5857ms 28.1011 Ops/s 27.8429 Ops/s $\color{#35bf28}+0.93\%$
test_values[td0_return_estimate-False-False] 0.2328ms 0.1649ms 6.0635 KOps/s 5.8114 KOps/s $\color{#35bf28}+4.34\%$
test_values[td1_return_estimate-False-False] 24.8566ms 22.3715ms 44.6998 Ops/s 43.8314 Ops/s $\color{#35bf28}+1.98\%$
test_values[vec_td1_return_estimate-False-False] 37.9202ms 35.6692ms 28.0354 Ops/s 27.7352 Ops/s $\color{#35bf28}+1.08\%$
test_values[td_lambda_return_estimate-True-False] 35.4216ms 32.1312ms 31.1224 Ops/s 29.6517 Ops/s $\color{#35bf28}+4.96\%$
test_values[vec_td_lambda_return_estimate-True-False] 37.5378ms 35.4893ms 28.1775 Ops/s 27.4503 Ops/s $\color{#35bf28}+2.65\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 11.2757ms 7.8541ms 127.3215 Ops/s 123.2438 Ops/s $\color{#35bf28}+3.31\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2206ms 1.9257ms 519.2890 Ops/s 557.5881 Ops/s $\textbf{\color{#d91a1a}-6.87\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4332ms 0.3470ms 2.8820 KOps/s 2.8125 KOps/s $\color{#35bf28}+2.47\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 48.3036ms 46.5873ms 21.4651 Ops/s 21.9394 Ops/s $\color{#d91a1a}-2.16\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.5773ms 3.0213ms 330.9838 Ops/s 328.9099 Ops/s $\color{#35bf28}+0.63\%$
test_dqn_speed 2.0386ms 1.3391ms 746.7978 Ops/s 729.5607 Ops/s $\color{#35bf28}+2.36\%$
test_ddpg_speed 3.1174ms 2.6750ms 373.8327 Ops/s 369.5886 Ops/s $\color{#35bf28}+1.15\%$
test_sac_speed 8.9695ms 8.2066ms 121.8525 Ops/s 111.8627 Ops/s $\textbf{\color{#35bf28}+8.93\%}$
test_redq_speed 14.2160ms 13.1243ms 76.1947 Ops/s 75.9158 Ops/s $\color{#35bf28}+0.37\%$
test_redq_deprec_speed 14.4195ms 12.9444ms 77.2536 Ops/s 76.4242 Ops/s $\color{#35bf28}+1.09\%$
test_td3_speed 16.0375ms 8.2305ms 121.4990 Ops/s 121.0660 Ops/s $\color{#35bf28}+0.36\%$
test_cql_speed 37.8974ms 36.0246ms 27.7588 Ops/s 26.8668 Ops/s $\color{#35bf28}+3.32\%$
test_a2c_speed 8.5834ms 7.3359ms 136.3158 Ops/s 129.0298 Ops/s $\textbf{\color{#35bf28}+5.65\%}$
test_ppo_speed 8.8366ms 7.7204ms 129.5266 Ops/s 125.7292 Ops/s $\color{#35bf28}+3.02\%$
test_reinforce_speed 7.4241ms 6.5585ms 152.4732 Ops/s 151.2863 Ops/s $\color{#35bf28}+0.78\%$
test_iql_speed 33.3956ms 32.3114ms 30.9489 Ops/s 30.3275 Ops/s $\color{#35bf28}+2.05\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.2124ms 2.2103ms 452.4261 Ops/s 461.4718 Ops/s $\color{#d91a1a}-1.96\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0139ms 0.4961ms 2.0156 KOps/s 1.9747 KOps/s $\color{#35bf28}+2.07\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7619ms 0.4714ms 2.1215 KOps/s 2.1190 KOps/s $\color{#35bf28}+0.12\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.4243ms 2.1104ms 473.8388 Ops/s 433.9835 Ops/s $\textbf{\color{#35bf28}+9.18\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0305ms 0.4829ms 2.0706 KOps/s 2.0480 KOps/s $\color{#35bf28}+1.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6331ms 0.4594ms 2.1768 KOps/s 2.1442 KOps/s $\color{#35bf28}+1.52\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7741ms 1.1987ms 834.2682 Ops/s 824.6347 Ops/s $\color{#35bf28}+1.17\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.7284ms 1.1330ms 882.6179 Ops/s 872.8358 Ops/s $\color{#35bf28}+1.12\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.5412ms 2.2331ms 447.7996 Ops/s 427.3902 Ops/s $\color{#35bf28}+4.78\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.1202s 0.7191ms 1.3906 KOps/s 1.6219 KOps/s $\textbf{\color{#d91a1a}-14.26\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8296ms 0.5814ms 1.7199 KOps/s 1.6991 KOps/s $\color{#35bf28}+1.22\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.6613ms 2.1505ms 465.0062 Ops/s 443.4799 Ops/s $\color{#35bf28}+4.85\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9235ms 0.4940ms 2.0243 KOps/s 2.0192 KOps/s $\color{#35bf28}+0.25\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7645ms 0.4761ms 2.1002 KOps/s 2.0726 KOps/s $\color{#35bf28}+1.33\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.7603ms 2.3021ms 434.3883 Ops/s 433.8847 Ops/s $\color{#35bf28}+0.12\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.5857ms 0.4897ms 2.0422 KOps/s 2.0618 KOps/s $\color{#d91a1a}-0.95\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6449ms 0.4640ms 2.1553 KOps/s 2.1429 KOps/s $\color{#35bf28}+0.58\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4891ms 2.3390ms 427.5274 Ops/s 441.7403 Ops/s $\color{#d91a1a}-3.22\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1604ms 0.6199ms 1.6131 KOps/s 1.6265 KOps/s $\color{#d91a1a}-0.82\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7603ms 0.5871ms 1.7034 KOps/s 1.7122 KOps/s $\color{#d91a1a}-0.51\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1193s 6.0208ms 166.0911 Ops/s 125.9980 Ops/s $\textbf{\color{#35bf28}+31.82\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 0.1069s 13.8445ms 72.2308 Ops/s 83.4440 Ops/s $\textbf{\color{#d91a1a}-13.44\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 4.2634ms 1.1514ms 868.5087 Ops/s 948.4485 Ops/s $\textbf{\color{#d91a1a}-8.43\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 97.7971ms 5.5242ms 181.0216 Ops/s 177.0611 Ops/s $\color{#35bf28}+2.24\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.6959ms 11.9735ms 83.5181 Ops/s 83.3318 Ops/s $\color{#35bf28}+0.22\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.5126ms 1.1577ms 863.7567 Ops/s 933.8694 Ops/s $\textbf{\color{#d91a1a}-7.51\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1016s 5.8939ms 169.6668 Ops/s 126.1455 Ops/s $\textbf{\color{#35bf28}+34.50\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1058s 14.3920ms 69.4831 Ops/s 81.4116 Ops/s $\textbf{\color{#d91a1a}-14.65\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.1107ms 1.3826ms 723.2556 Ops/s 721.1488 Ops/s $\color{#35bf28}+0.29\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 27, 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: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 90.0094ms 89.8582ms 11.1287 Ops/s 10.8126 Ops/s $\color{#35bf28}+2.92\%$
test_sync 84.0525ms 83.5977ms 11.9621 Ops/s 11.9850 Ops/s $\color{#d91a1a}-0.19\%$
test_async 0.1595s 68.4169ms 14.6163 Ops/s 14.6770 Ops/s $\color{#d91a1a}-0.41\%$
test_single_pixels 0.1020s 0.1006s 9.9419 Ops/s 9.8817 Ops/s $\color{#35bf28}+0.61\%$
test_sync_pixels 65.1641ms 63.1911ms 15.8250 Ops/s 15.6424 Ops/s $\color{#35bf28}+1.17\%$
test_async_pixels 0.1172s 53.0723ms 18.8422 Ops/s 18.5069 Ops/s $\color{#35bf28}+1.81\%$
test_simple 0.6810s 0.6163s 1.6225 Ops/s 1.6154 Ops/s $\color{#35bf28}+0.44\%$
test_transformed 0.8749s 0.8076s 1.2383 Ops/s 1.2232 Ops/s $\color{#35bf28}+1.24\%$
test_serial 1.9006s 1.8360s 0.5447 Ops/s 0.5372 Ops/s $\color{#35bf28}+1.38\%$
test_parallel 1.7238s 1.6589s 0.6028 Ops/s 0.5984 Ops/s $\color{#35bf28}+0.74\%$
test_step_mdp_speed[True-True-True-True-True] 81.0110μs 26.4369μs 37.8259 KOps/s 38.7031 KOps/s $\color{#d91a1a}-2.27\%$
test_step_mdp_speed[True-True-True-True-False] 41.3810μs 16.0306μs 62.3808 KOps/s 63.3099 KOps/s $\color{#d91a1a}-1.47\%$
test_step_mdp_speed[True-True-True-False-True] 34.9210μs 15.0130μs 66.6091 KOps/s 67.2478 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[True-True-True-False-False] 27.6610μs 9.2383μs 108.2448 KOps/s 109.1638 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[True-True-False-True-True] 58.6310μs 27.7880μs 35.9868 KOps/s 36.6160 KOps/s $\color{#d91a1a}-1.72\%$
test_step_mdp_speed[True-True-False-True-False] 48.7610μs 17.7603μs 56.3054 KOps/s 57.5271 KOps/s $\color{#d91a1a}-2.12\%$
test_step_mdp_speed[True-True-False-False-True] 36.5310μs 16.7330μs 59.7620 KOps/s 60.4594 KOps/s $\color{#d91a1a}-1.15\%$
test_step_mdp_speed[True-True-False-False-False] 32.5310μs 10.9003μs 91.7403 KOps/s 92.9907 KOps/s $\color{#d91a1a}-1.34\%$
test_step_mdp_speed[True-False-True-True-True] 0.1518ms 29.6097μs 33.7728 KOps/s 34.1125 KOps/s $\color{#d91a1a}-1.00\%$
test_step_mdp_speed[True-False-True-True-False] 42.4000μs 19.5017μs 51.2775 KOps/s 52.3334 KOps/s $\color{#d91a1a}-2.02\%$
test_step_mdp_speed[True-False-True-False-True] 38.6910μs 16.7142μs 59.8293 KOps/s 60.7470 KOps/s $\color{#d91a1a}-1.51\%$
test_step_mdp_speed[True-False-True-False-False] 52.0410μs 10.9657μs 91.1933 KOps/s 93.0783 KOps/s $\color{#d91a1a}-2.03\%$
test_step_mdp_speed[True-False-False-True-True] 55.8410μs 31.2288μs 32.0217 KOps/s 32.7530 KOps/s $\color{#d91a1a}-2.23\%$
test_step_mdp_speed[True-False-False-True-False] 43.5210μs 21.0447μs 47.5178 KOps/s 48.4267 KOps/s $\color{#d91a1a}-1.88\%$
test_step_mdp_speed[True-False-False-False-True] 56.8010μs 18.1948μs 54.9609 KOps/s 56.0644 KOps/s $\color{#d91a1a}-1.97\%$
test_step_mdp_speed[True-False-False-False-False] 35.4210μs 12.5149μs 79.9051 KOps/s 81.1898 KOps/s $\color{#d91a1a}-1.58\%$
test_step_mdp_speed[False-True-True-True-True] 59.8410μs 29.6907μs 33.6806 KOps/s 33.9780 KOps/s $\color{#d91a1a}-0.88\%$
test_step_mdp_speed[False-True-True-True-False] 42.6110μs 19.4769μs 51.3430 KOps/s 52.2328 KOps/s $\color{#d91a1a}-1.70\%$
test_step_mdp_speed[False-True-True-False-True] 35.3510μs 19.8655μs 50.3385 KOps/s 50.4731 KOps/s $\color{#d91a1a}-0.27\%$
test_step_mdp_speed[False-True-True-False-False] 54.2610μs 12.4703μs 80.1905 KOps/s 81.5567 KOps/s $\color{#d91a1a}-1.68\%$
test_step_mdp_speed[False-True-False-True-True] 55.7810μs 31.4429μs 31.8037 KOps/s 32.9623 KOps/s $\color{#d91a1a}-3.51\%$
test_step_mdp_speed[False-True-False-True-False] 45.0200μs 21.1210μs 47.3463 KOps/s 48.7795 KOps/s $\color{#d91a1a}-2.94\%$
test_step_mdp_speed[False-True-False-False-True] 50.7810μs 21.1047μs 47.3829 KOps/s 48.3448 KOps/s $\color{#d91a1a}-1.99\%$
test_step_mdp_speed[False-True-False-False-False] 43.5810μs 14.0956μs 70.9443 KOps/s 72.4336 KOps/s $\color{#d91a1a}-2.06\%$
test_step_mdp_speed[False-False-True-True-True] 56.3910μs 32.9672μs 30.3332 KOps/s 31.2317 KOps/s $\color{#d91a1a}-2.88\%$
test_step_mdp_speed[False-False-True-True-False] 45.8510μs 22.8001μs 43.8595 KOps/s 44.8330 KOps/s $\color{#d91a1a}-2.17\%$
test_step_mdp_speed[False-False-True-False-True] 51.6610μs 21.1256μs 47.3359 KOps/s 48.2810 KOps/s $\color{#d91a1a}-1.96\%$
test_step_mdp_speed[False-False-True-False-False] 45.1710μs 14.0263μs 71.2949 KOps/s 72.5713 KOps/s $\color{#d91a1a}-1.76\%$
test_step_mdp_speed[False-False-False-True-True] 65.7010μs 34.3080μs 29.1477 KOps/s 29.9922 KOps/s $\color{#d91a1a}-2.82\%$
test_step_mdp_speed[False-False-False-True-False] 45.4610μs 24.6882μs 40.5052 KOps/s 41.9696 KOps/s $\color{#d91a1a}-3.49\%$
test_step_mdp_speed[False-False-False-False-True] 80.4520μs 22.6109μs 44.2264 KOps/s 45.1196 KOps/s $\color{#d91a1a}-1.98\%$
test_step_mdp_speed[False-False-False-False-False] 44.7710μs 15.6691μs 63.8201 KOps/s 65.5373 KOps/s $\color{#d91a1a}-2.62\%$
test_values[generalized_advantage_estimate-True-True] 22.4707ms 21.9446ms 45.5692 Ops/s 45.7776 Ops/s $\color{#d91a1a}-0.46\%$
test_values[vec_generalized_advantage_estimate-True-True] 81.8037ms 3.1825ms 314.2143 Ops/s 313.7224 Ops/s $\color{#35bf28}+0.16\%$
test_values[td0_return_estimate-False-False] 84.6520μs 59.4564μs 16.8191 KOps/s 16.3402 KOps/s $\color{#35bf28}+2.93\%$
test_values[td1_return_estimate-False-False] 49.8843ms 49.2924ms 20.2871 Ops/s 20.2169 Ops/s $\color{#35bf28}+0.35\%$
test_values[vec_td1_return_estimate-False-False] 2.0835ms 1.7319ms 577.3906 Ops/s 576.6756 Ops/s $\color{#35bf28}+0.12\%$
test_values[td_lambda_return_estimate-True-False] 78.9137ms 78.4642ms 12.7447 Ops/s 12.6387 Ops/s $\color{#35bf28}+0.84\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.0618ms 1.7302ms 577.9815 Ops/s 576.4269 Ops/s $\color{#35bf28}+0.27\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 22.0188ms 21.6436ms 46.2030 Ops/s 46.1687 Ops/s $\color{#35bf28}+0.07\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8559ms 0.6573ms 1.5213 KOps/s 1.4995 KOps/s $\color{#35bf28}+1.45\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6792ms 0.6195ms 1.6143 KOps/s 1.6045 KOps/s $\color{#35bf28}+0.61\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.4813ms 1.4210ms 703.7503 Ops/s 702.7202 Ops/s $\color{#35bf28}+0.15\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9125ms 0.6409ms 1.5603 KOps/s 1.5564 KOps/s $\color{#35bf28}+0.25\%$
test_dqn_speed 8.1190ms 1.2744ms 784.6570 Ops/s 761.0259 Ops/s $\color{#35bf28}+3.11\%$
test_ddpg_speed 2.7255ms 2.4524ms 407.7632 Ops/s 400.0455 Ops/s $\color{#35bf28}+1.93\%$
test_sac_speed 7.8029ms 7.2638ms 137.6689 Ops/s 135.2810 Ops/s $\color{#35bf28}+1.77\%$
test_redq_speed 10.1232ms 9.3067ms 107.4491 Ops/s 104.8683 Ops/s $\color{#35bf28}+2.46\%$
test_redq_deprec_speed 10.5736ms 10.0488ms 99.5146 Ops/s 96.5200 Ops/s $\color{#35bf28}+3.10\%$
test_td3_speed 7.3305ms 7.2027ms 138.8374 Ops/s 135.0889 Ops/s $\color{#35bf28}+2.77\%$
test_cql_speed 24.7140ms 23.6151ms 42.3458 Ops/s 38.0580 Ops/s $\textbf{\color{#35bf28}+11.27\%}$
test_a2c_speed 5.4783ms 5.2816ms 189.3381 Ops/s 187.5225 Ops/s $\color{#35bf28}+0.97\%$
test_ppo_speed 5.7988ms 5.6228ms 177.8478 Ops/s 175.9235 Ops/s $\color{#35bf28}+1.09\%$
test_reinforce_speed 4.6112ms 4.3121ms 231.9079 Ops/s 230.0224 Ops/s $\color{#35bf28}+0.82\%$
test_iql_speed 18.7782ms 18.2419ms 54.8188 Ops/s 54.3345 Ops/s $\color{#35bf28}+0.89\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.5647ms 2.4547ms 407.3854 Ops/s 403.3466 Ops/s $\color{#35bf28}+1.00\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1759ms 0.5100ms 1.9608 KOps/s 1.9521 KOps/s $\color{#35bf28}+0.44\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6961ms 0.4916ms 2.0340 KOps/s 2.0203 KOps/s $\color{#35bf28}+0.68\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.5761ms 2.4676ms 405.2449 Ops/s 401.8871 Ops/s $\color{#35bf28}+0.84\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2718ms 0.5032ms 1.9874 KOps/s 1.9688 KOps/s $\color{#35bf28}+0.94\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6775ms 0.4853ms 2.0608 KOps/s 2.0404 KOps/s $\color{#35bf28}+1.00\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 4.4562ms 1.3366ms 748.1433 Ops/s 747.7643 Ops/s $\color{#35bf28}+0.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4286ms 1.2757ms 783.8649 Ops/s 779.6561 Ops/s $\color{#35bf28}+0.54\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.6636ms 2.5744ms 388.4327 Ops/s 387.4483 Ops/s $\color{#35bf28}+0.25\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8239ms 0.6252ms 1.5995 KOps/s 1.5836 KOps/s $\color{#35bf28}+1.00\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 6.4492ms 0.6117ms 1.6347 KOps/s 1.6310 KOps/s $\color{#35bf28}+0.23\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.5332ms 2.4548ms 407.3597 Ops/s 408.6927 Ops/s $\color{#d91a1a}-0.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6259ms 0.5113ms 1.9560 KOps/s 1.9395 KOps/s $\color{#35bf28}+0.85\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.8059ms 0.4974ms 2.0104 KOps/s 2.0177 KOps/s $\color{#d91a1a}-0.36\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.6410ms 2.4980ms 400.3140 Ops/s 400.9826 Ops/s $\color{#d91a1a}-0.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6284ms 0.5047ms 1.9813 KOps/s 1.9748 KOps/s $\color{#35bf28}+0.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6860ms 0.4858ms 2.0585 KOps/s 2.0229 KOps/s $\color{#35bf28}+1.76\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.6855ms 2.5915ms 385.8821 Ops/s 383.7189 Ops/s $\color{#35bf28}+0.56\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2387ms 0.6284ms 1.5914 KOps/s 1.5738 KOps/s $\color{#35bf28}+1.12\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7974ms 0.6077ms 1.6454 KOps/s 1.6342 KOps/s $\color{#35bf28}+0.69\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1266s 6.7948ms 147.1709 Ops/s 147.1625 Ops/s $+0.01\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.7904ms 12.3462ms 80.9968 Ops/s 81.4583 Ops/s $\color{#d91a1a}-0.57\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.0721ms 1.0257ms 974.9329 Ops/s 957.2467 Ops/s $\color{#35bf28}+1.85\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1129s 6.5225ms 153.3148 Ops/s 114.5270 Ops/s $\textbf{\color{#35bf28}+33.87\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.1227s 14.4876ms 69.0246 Ops/s 81.4964 Ops/s $\textbf{\color{#d91a1a}-15.30\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.5502ms 1.1399ms 877.2400 Ops/s 956.3611 Ops/s $\textbf{\color{#d91a1a}-8.27\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1143s 6.8913ms 145.1115 Ops/s 143.7177 Ops/s $\color{#35bf28}+0.97\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 14.8935ms 12.6617ms 78.9786 Ops/s 80.1354 Ops/s $\color{#d91a1a}-1.44\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.5855ms 1.4952ms 668.7911 Ops/s 712.8232 Ops/s $\textbf{\color{#d91a1a}-6.18\%}$

@vmoens vmoens merged commit c98754f into main Mar 27, 2024
63 of 67 checks passed
@vmoens vmoens deleted the fix-truncated-slicesampler branch March 27, 2024 19:26
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
bug Something isn't working 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