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] Use same signature for append_transform in all cases #2091

Merged
merged 2 commits into from
Apr 18, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Apr 18, 2024

No description provided.

Copy link

pytorch-bot bot commented Apr 18, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2091

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

❌ 1 New Failure, 4 Unrelated Failures

As of commit 3c43efb with merge base 6b87184 (image):

NEW FAILURE - The following job has 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.

@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 Apr 18, 2024
@vmoens vmoens added the bug Something isn't working label Apr 18, 2024
Copy link

github-actions bot commented Apr 18, 2024

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}7$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 67.7465ms 55.0791ms 18.1557 Ops/s 17.5953 Ops/s $\color{#35bf28}+3.18\%$
test_sync 34.7533ms 29.5935ms 33.7912 Ops/s 32.3611 Ops/s $\color{#35bf28}+4.42\%$
test_async 62.8227ms 29.0788ms 34.3894 Ops/s 35.7785 Ops/s $\color{#d91a1a}-3.88\%$
test_simple 0.4265s 0.3595s 2.7817 Ops/s 2.9076 Ops/s $\color{#d91a1a}-4.33\%$
test_transformed 0.4867s 0.4852s 2.0609 Ops/s 1.9994 Ops/s $\color{#35bf28}+3.08\%$
test_serial 1.2484s 1.2019s 0.8320 Ops/s 0.8177 Ops/s $\color{#35bf28}+1.75\%$
test_parallel 1.0728s 1.0289s 0.9720 Ops/s 0.9888 Ops/s $\color{#d91a1a}-1.70\%$
test_step_mdp_speed[True-True-True-True-True] 0.2025ms 21.0145μs 47.5863 KOps/s 46.4429 KOps/s $\color{#35bf28}+2.46\%$
test_step_mdp_speed[True-True-True-True-False] 39.7840μs 12.8300μs 77.9425 KOps/s 76.7237 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[True-True-True-False-True] 39.4240μs 12.4327μs 80.4332 KOps/s 80.0462 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[True-True-True-False-False] 28.4330μs 7.4905μs 133.5017 KOps/s 132.8104 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-True-False-True-True] 62.1960μs 22.3993μs 44.6443 KOps/s 43.9337 KOps/s $\color{#35bf28}+1.62\%$
test_step_mdp_speed[True-True-False-True-False] 36.7490μs 14.0451μs 71.1993 KOps/s 69.8948 KOps/s $\color{#35bf28}+1.87\%$
test_step_mdp_speed[True-True-False-False-True] 38.4720μs 13.6014μs 73.5220 KOps/s 73.5434 KOps/s $\color{#d91a1a}-0.03\%$
test_step_mdp_speed[True-True-False-False-False] 35.6170μs 8.6355μs 115.8006 KOps/s 114.2504 KOps/s $\color{#35bf28}+1.36\%$
test_step_mdp_speed[True-False-True-True-True] 56.2560μs 23.7201μs 42.1584 KOps/s 41.7847 KOps/s $\color{#35bf28}+0.89\%$
test_step_mdp_speed[True-False-True-True-False] 46.1760μs 15.3785μs 65.0257 KOps/s 63.9476 KOps/s $\color{#35bf28}+1.69\%$
test_step_mdp_speed[True-False-True-False-True] 63.6890μs 13.6422μs 73.3021 KOps/s 73.4331 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[True-False-True-False-False] 31.7390μs 8.7292μs 114.5582 KOps/s 114.8750 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[True-False-False-True-True] 59.6610μs 24.8289μs 40.2756 KOps/s 39.7002 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[True-False-False-True-False] 47.1780μs 16.4107μs 60.9357 KOps/s 59.4048 KOps/s $\color{#35bf28}+2.58\%$
test_step_mdp_speed[True-False-False-False-True] 38.9630μs 14.6135μs 68.4299 KOps/s 67.3595 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[True-False-False-False-False] 44.2930μs 9.8251μs 101.7796 KOps/s 99.9060 KOps/s $\color{#35bf28}+1.88\%$
test_step_mdp_speed[False-True-True-True-True] 56.1850μs 23.6817μs 42.2266 KOps/s 41.2290 KOps/s $\color{#35bf28}+2.42\%$
test_step_mdp_speed[False-True-True-True-False] 43.5320μs 15.4297μs 64.8102 KOps/s 64.3183 KOps/s $\color{#35bf28}+0.76\%$
test_step_mdp_speed[False-True-True-False-True] 44.6630μs 15.6950μs 63.7146 KOps/s 63.1143 KOps/s $\color{#35bf28}+0.95\%$
test_step_mdp_speed[False-True-True-False-False] 33.5530μs 9.8879μs 101.1332 KOps/s 99.9735 KOps/s $\color{#35bf28}+1.16\%$
test_step_mdp_speed[False-True-False-True-True] 36.5780μs 25.2175μs 39.6550 KOps/s 38.7024 KOps/s $\color{#35bf28}+2.46\%$
test_step_mdp_speed[False-True-False-True-False] 45.1850μs 16.7195μs 59.8106 KOps/s 59.7597 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[False-True-False-False-True] 0.1023ms 16.7127μs 59.8348 KOps/s 58.0950 KOps/s $\color{#35bf28}+2.99\%$
test_step_mdp_speed[False-True-False-False-False] 57.9480μs 10.9745μs 91.1202 KOps/s 89.1772 KOps/s $\color{#35bf28}+2.18\%$
test_step_mdp_speed[False-False-True-True-True] 79.4880μs 26.1287μs 38.2721 KOps/s 37.8194 KOps/s $\color{#35bf28}+1.20\%$
test_step_mdp_speed[False-False-True-True-False] 47.3790μs 17.8028μs 56.1709 KOps/s 55.3262 KOps/s $\color{#35bf28}+1.53\%$
test_step_mdp_speed[False-False-True-False-True] 50.0040μs 16.6832μs 59.9406 KOps/s 58.4208 KOps/s $\color{#35bf28}+2.60\%$
test_step_mdp_speed[False-False-True-False-False] 36.2480μs 11.0077μs 90.8453 KOps/s 89.5924 KOps/s $\color{#35bf28}+1.40\%$
test_step_mdp_speed[False-False-False-True-True] 68.6080μs 27.1228μs 36.8693 KOps/s 36.2468 KOps/s $\color{#35bf28}+1.72\%$
test_step_mdp_speed[False-False-False-True-False] 51.4150μs 18.7921μs 53.2137 KOps/s 52.3589 KOps/s $\color{#35bf28}+1.63\%$
test_step_mdp_speed[False-False-False-False-True] 44.6030μs 17.7106μs 56.4635 KOps/s 54.8943 KOps/s $\color{#35bf28}+2.86\%$
test_step_mdp_speed[False-False-False-False-False] 35.8370μs 12.1210μs 82.5015 KOps/s 80.7992 KOps/s $\color{#35bf28}+2.11\%$
test_values[generalized_advantage_estimate-True-True] 11.6234ms 9.2285ms 108.3597 Ops/s 104.1972 Ops/s $\color{#35bf28}+3.99\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.5665ms 33.6701ms 29.7000 Ops/s 29.8431 Ops/s $\color{#d91a1a}-0.48\%$
test_values[td0_return_estimate-False-False] 0.3334ms 0.2057ms 4.8619 KOps/s 5.4950 KOps/s $\textbf{\color{#d91a1a}-11.52\%}$
test_values[td1_return_estimate-False-False] 23.2297ms 22.8565ms 43.7512 Ops/s 41.6903 Ops/s $\color{#35bf28}+4.94\%$
test_values[vec_td1_return_estimate-False-False] 34.7401ms 33.5839ms 29.7761 Ops/s 29.7633 Ops/s $\color{#35bf28}+0.04\%$
test_values[td_lambda_return_estimate-True-False] 35.6261ms 33.2038ms 30.1170 Ops/s 29.2349 Ops/s $\color{#35bf28}+3.02\%$
test_values[vec_td_lambda_return_estimate-True-False] 34.7046ms 33.7090ms 29.6656 Ops/s 29.8052 Ops/s $\color{#d91a1a}-0.47\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.4604ms 7.9924ms 125.1183 Ops/s 121.1408 Ops/s $\color{#35bf28}+3.28\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3471ms 1.9816ms 504.6332 Ops/s 484.4652 Ops/s $\color{#35bf28}+4.16\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6667ms 0.3615ms 2.7664 KOps/s 2.7788 KOps/s $\color{#d91a1a}-0.45\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 44.1632ms 42.6707ms 23.4353 Ops/s 24.7235 Ops/s $\textbf{\color{#d91a1a}-5.21\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.1897ms 3.0346ms 329.5370 Ops/s 325.5208 Ops/s $\color{#35bf28}+1.23\%$
test_dqn_speed 1.8688ms 1.3450ms 743.4766 Ops/s 729.0764 Ops/s $\color{#35bf28}+1.98\%$
test_ddpg_speed 3.4629ms 2.6899ms 371.7654 Ops/s 369.0046 Ops/s $\color{#35bf28}+0.75\%$
test_sac_speed 9.4833ms 8.3884ms 119.2124 Ops/s 118.4667 Ops/s $\color{#35bf28}+0.63\%$
test_redq_speed 15.4749ms 13.7754ms 72.5934 Ops/s 73.2415 Ops/s $\color{#d91a1a}-0.88\%$
test_redq_deprec_speed 14.9193ms 14.0400ms 71.2252 Ops/s 71.7897 Ops/s $\color{#d91a1a}-0.79\%$
test_td3_speed 17.6562ms 8.4530ms 118.3008 Ops/s 119.6067 Ops/s $\color{#d91a1a}-1.09\%$
test_cql_speed 37.9297ms 36.5010ms 27.3965 Ops/s 27.2959 Ops/s $\color{#35bf28}+0.37\%$
test_a2c_speed 8.4183ms 7.4015ms 135.1082 Ops/s 128.6503 Ops/s $\textbf{\color{#35bf28}+5.02\%}$
test_ppo_speed 8.3257ms 7.6812ms 130.1873 Ops/s 124.0086 Ops/s $\color{#35bf28}+4.98\%$
test_reinforce_speed 7.6313ms 6.6893ms 149.4936 Ops/s 145.1364 Ops/s $\color{#35bf28}+3.00\%$
test_iql_speed 34.3818ms 33.2629ms 30.0635 Ops/s 30.1199 Ops/s $\color{#d91a1a}-0.19\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.3996ms 2.5359ms 394.3418 Ops/s 420.4620 Ops/s $\textbf{\color{#d91a1a}-6.21\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.1088s 0.5915ms 1.6906 KOps/s 1.9840 KOps/s $\textbf{\color{#d91a1a}-14.79\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7546ms 0.4844ms 2.0645 KOps/s 2.0934 KOps/s $\color{#d91a1a}-1.38\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9403ms 2.5363ms 394.2683 Ops/s 414.9597 Ops/s $\color{#d91a1a}-4.99\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1789ms 0.4978ms 2.0088 KOps/s 2.0160 KOps/s $\color{#d91a1a}-0.36\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6503ms 0.4658ms 2.1469 KOps/s 2.0932 KOps/s $\color{#35bf28}+2.57\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7405ms 1.2285ms 813.9943 Ops/s 794.0651 Ops/s $\color{#35bf28}+2.51\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6688ms 1.1613ms 861.1383 Ops/s 845.1462 Ops/s $\color{#35bf28}+1.89\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.9085ms 2.5244ms 396.1327 Ops/s 392.1738 Ops/s $\color{#35bf28}+1.01\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1027ms 0.6234ms 1.6040 KOps/s 1.5763 KOps/s $\color{#35bf28}+1.76\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9259ms 0.5989ms 1.6697 KOps/s 1.6743 KOps/s $\color{#d91a1a}-0.27\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.8589ms 2.4632ms 405.9711 Ops/s 396.0973 Ops/s $\color{#35bf28}+2.49\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0069ms 0.5104ms 1.9593 KOps/s 1.9515 KOps/s $\color{#35bf28}+0.40\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5930ms 0.4842ms 2.0652 KOps/s 2.0075 KOps/s $\color{#35bf28}+2.87\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.7070ms 2.5027ms 399.5711 Ops/s 410.6239 Ops/s $\color{#d91a1a}-2.69\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7808ms 0.5062ms 1.9754 KOps/s 2.0023 KOps/s $\color{#d91a1a}-1.34\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.2251ms 0.4932ms 2.0275 KOps/s 2.0299 KOps/s $\color{#d91a1a}-0.12\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.5395ms 2.4768ms 403.7512 Ops/s 375.2134 Ops/s $\textbf{\color{#35bf28}+7.61\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2349ms 0.6256ms 1.5984 KOps/s 1.5565 KOps/s $\color{#35bf28}+2.69\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9677ms 0.6021ms 1.6607 KOps/s 1.6433 KOps/s $\color{#35bf28}+1.06\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1175s 7.9119ms 126.3920 Ops/s 124.0030 Ops/s $\color{#35bf28}+1.93\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.1664ms 12.1512ms 82.2963 Ops/s 81.4509 Ops/s $\color{#35bf28}+1.04\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 4.4938ms 1.1592ms 862.6357 Ops/s 945.7623 Ops/s $\textbf{\color{#d91a1a}-8.79\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1040s 5.6359ms 177.4347 Ops/s 171.0898 Ops/s $\color{#35bf28}+3.71\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.5074ms 12.1091ms 82.5825 Ops/s 69.4069 Ops/s $\textbf{\color{#35bf28}+18.98\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.0047ms 1.1484ms 870.7405 Ops/s 945.7668 Ops/s $\textbf{\color{#d91a1a}-7.93\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1214s 8.8386ms 113.1407 Ops/s 164.5924 Ops/s $\textbf{\color{#d91a1a}-31.26\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 14.9243ms 12.5666ms 79.5759 Ops/s 78.0136 Ops/s $\color{#35bf28}+2.00\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 1.9730ms 1.3777ms 725.8557 Ops/s 703.2522 Ops/s $\color{#35bf28}+3.21\%$

Copy link

$\color{#35bf28}\textsf{\Large✔\kern{0.2cm}\normalsize OK}$ Result of GPU Benchmark Tests

Total Benchmarks: 94. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}0$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 99.9709ms 95.8352ms 10.4346 Ops/s 9.5221 Ops/s $\textbf{\color{#35bf28}+9.58\%}$
test_sync 86.5446ms 85.7442ms 11.6626 Ops/s 11.6244 Ops/s $\color{#35bf28}+0.33\%$
test_async 0.1601s 69.7685ms 14.3331 Ops/s 14.3755 Ops/s $\color{#d91a1a}-0.29\%$
test_single_pixels 0.1081s 0.1076s 9.2911 Ops/s 9.1495 Ops/s $\color{#35bf28}+1.55\%$
test_sync_pixels 67.1140ms 65.6177ms 15.2398 Ops/s 15.4310 Ops/s $\color{#d91a1a}-1.24\%$
test_async_pixels 0.1199s 54.6516ms 18.2977 Ops/s 17.8927 Ops/s $\color{#35bf28}+2.26\%$
test_simple 0.7200s 0.6595s 1.5163 Ops/s 1.4972 Ops/s $\color{#35bf28}+1.27\%$
test_transformed 0.9332s 0.8698s 1.1496 Ops/s 1.1262 Ops/s $\color{#35bf28}+2.08\%$
test_serial 2.0472s 1.9855s 0.5037 Ops/s 0.4934 Ops/s $\color{#35bf28}+2.08\%$
test_parallel 1.8166s 1.7523s 0.5707 Ops/s 0.5826 Ops/s $\color{#d91a1a}-2.05\%$
test_step_mdp_speed[True-True-True-True-True] 93.0850μs 32.2058μs 31.0504 KOps/s 31.1400 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[True-True-True-True-False] 35.8420μs 18.8453μs 53.0636 KOps/s 51.5480 KOps/s $\color{#35bf28}+2.94\%$
test_step_mdp_speed[True-True-True-False-True] 78.2840μs 17.8672μs 55.9685 KOps/s 53.9766 KOps/s $\color{#35bf28}+3.69\%$
test_step_mdp_speed[True-True-True-False-False] 30.1720μs 10.7795μs 92.7690 KOps/s 89.6977 KOps/s $\color{#35bf28}+3.42\%$
test_step_mdp_speed[True-True-False-True-True] 52.0430μs 33.6525μs 29.7155 KOps/s 29.2905 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[True-True-False-True-False] 94.6850μs 20.7164μs 48.2709 KOps/s 47.3205 KOps/s $\color{#35bf28}+2.01\%$
test_step_mdp_speed[True-True-False-False-True] 38.7020μs 19.5888μs 51.0495 KOps/s 49.6557 KOps/s $\color{#35bf28}+2.81\%$
test_step_mdp_speed[True-True-False-False-False] 36.4620μs 12.5951μs 79.3961 KOps/s 77.2108 KOps/s $\color{#35bf28}+2.83\%$
test_step_mdp_speed[True-False-True-True-True] 52.1920μs 35.4891μs 28.1777 KOps/s 27.8350 KOps/s $\color{#35bf28}+1.23\%$
test_step_mdp_speed[True-False-True-True-False] 38.6020μs 22.4869μs 44.4703 KOps/s 42.5113 KOps/s $\color{#35bf28}+4.61\%$
test_step_mdp_speed[True-False-True-False-True] 0.2061ms 19.7581μs 50.6122 KOps/s 49.7241 KOps/s $\color{#35bf28}+1.79\%$
test_step_mdp_speed[True-False-True-False-False] 0.2007ms 12.5683μs 79.5652 KOps/s 77.0658 KOps/s $\color{#35bf28}+3.24\%$
test_step_mdp_speed[True-False-False-True-True] 53.8620μs 36.8188μs 27.1600 KOps/s 26.3495 KOps/s $\color{#35bf28}+3.08\%$
test_step_mdp_speed[True-False-False-True-False] 47.2330μs 24.3525μs 41.0636 KOps/s 40.2326 KOps/s $\color{#35bf28}+2.07\%$
test_step_mdp_speed[True-False-False-False-True] 39.9520μs 21.4084μs 46.7107 KOps/s 45.8754 KOps/s $\color{#35bf28}+1.82\%$
test_step_mdp_speed[True-False-False-False-False] 35.2820μs 14.3018μs 69.9212 KOps/s 67.8982 KOps/s $\color{#35bf28}+2.98\%$
test_step_mdp_speed[False-True-True-True-True] 56.0230μs 35.7096μs 28.0037 KOps/s 27.5992 KOps/s $\color{#35bf28}+1.47\%$
test_step_mdp_speed[False-True-True-True-False] 42.0520μs 22.5380μs 44.3696 KOps/s 43.0294 KOps/s $\color{#35bf28}+3.11\%$
test_step_mdp_speed[False-True-True-False-True] 51.9030μs 23.7067μs 42.1822 KOps/s 41.4984 KOps/s $\color{#35bf28}+1.65\%$
test_step_mdp_speed[False-True-True-False-False] 30.1920μs 14.4331μs 69.2851 KOps/s 66.8626 KOps/s $\color{#35bf28}+3.62\%$
test_step_mdp_speed[False-True-False-True-True] 60.5530μs 37.1578μs 26.9122 KOps/s 26.4420 KOps/s $\color{#35bf28}+1.78\%$
test_step_mdp_speed[False-True-False-True-False] 40.0530μs 24.2563μs 41.2263 KOps/s 39.7615 KOps/s $\color{#35bf28}+3.68\%$
test_step_mdp_speed[False-True-False-False-True] 43.4220μs 25.4011μs 39.3684 KOps/s 38.4428 KOps/s $\color{#35bf28}+2.41\%$
test_step_mdp_speed[False-True-False-False-False] 32.0820μs 16.1626μs 61.8712 KOps/s 59.9919 KOps/s $\color{#35bf28}+3.13\%$
test_step_mdp_speed[False-False-True-True-True] 64.9440μs 39.3564μs 25.4088 KOps/s 25.2570 KOps/s $\color{#35bf28}+0.60\%$
test_step_mdp_speed[False-False-True-True-False] 40.9620μs 26.5166μs 37.7122 KOps/s 36.8544 KOps/s $\color{#35bf28}+2.33\%$
test_step_mdp_speed[False-False-True-False-True] 42.4920μs 25.4099μs 39.3547 KOps/s 38.7156 KOps/s $\color{#35bf28}+1.65\%$
test_step_mdp_speed[False-False-True-False-False] 32.4320μs 16.0965μs 62.1254 KOps/s 60.1178 KOps/s $\color{#35bf28}+3.34\%$
test_step_mdp_speed[False-False-False-True-True] 63.3140μs 40.7281μs 24.5531 KOps/s 24.2107 KOps/s $\color{#35bf28}+1.41\%$
test_step_mdp_speed[False-False-False-True-False] 51.8030μs 28.0444μs 35.6578 KOps/s 34.8276 KOps/s $\color{#35bf28}+2.38\%$
test_step_mdp_speed[False-False-False-False-True] 40.2420μs 26.8001μs 37.3133 KOps/s 36.3503 KOps/s $\color{#35bf28}+2.65\%$
test_step_mdp_speed[False-False-False-False-False] 38.9220μs 17.7014μs 56.4927 KOps/s 54.2656 KOps/s $\color{#35bf28}+4.10\%$
test_values[generalized_advantage_estimate-True-True] 22.3432ms 21.7180ms 46.0447 Ops/s 44.4198 Ops/s $\color{#35bf28}+3.66\%$
test_values[vec_generalized_advantage_estimate-True-True] 79.7580ms 3.1230ms 320.2036 Ops/s 318.3382 Ops/s $\color{#35bf28}+0.59\%$
test_values[td0_return_estimate-False-False] 88.0840μs 58.5395μs 17.0825 KOps/s 16.2219 KOps/s $\textbf{\color{#35bf28}+5.30\%}$
test_values[td1_return_estimate-False-False] 47.5409ms 46.3464ms 21.5767 Ops/s 20.5667 Ops/s $\color{#35bf28}+4.91\%$
test_values[vec_td1_return_estimate-False-False] 1.9550ms 1.7039ms 586.8744 Ops/s 582.4715 Ops/s $\color{#35bf28}+0.76\%$
test_values[td_lambda_return_estimate-True-False] 74.8452ms 73.9034ms 13.5312 Ops/s 12.9378 Ops/s $\color{#35bf28}+4.59\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.0443ms 1.7047ms 586.6261 Ops/s 582.7640 Ops/s $\color{#35bf28}+0.66\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 20.8225ms 20.4649ms 48.8642 Ops/s 45.7834 Ops/s $\textbf{\color{#35bf28}+6.73\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8457ms 0.6425ms 1.5565 KOps/s 1.5068 KOps/s $\color{#35bf28}+3.30\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7716ms 0.5913ms 1.6911 KOps/s 1.6408 KOps/s $\color{#35bf28}+3.07\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5609ms 1.4026ms 712.9575 Ops/s 702.7348 Ops/s $\color{#35bf28}+1.45\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9069ms 0.6185ms 1.6169 KOps/s 1.5829 KOps/s $\color{#35bf28}+2.15\%$
test_dqn_speed 8.7068ms 1.4030ms 712.7504 Ops/s 704.0717 Ops/s $\color{#35bf28}+1.23\%$
test_ddpg_speed 2.9945ms 2.6980ms 370.6482 Ops/s 368.5315 Ops/s $\color{#35bf28}+0.57\%$
test_sac_speed 8.4204ms 7.9510ms 125.7704 Ops/s 124.3837 Ops/s $\color{#35bf28}+1.11\%$
test_redq_speed 11.3162ms 10.2951ms 97.1338 Ops/s 95.5389 Ops/s $\color{#35bf28}+1.67\%$
test_redq_deprec_speed 11.7615ms 11.1403ms 89.7644 Ops/s 90.0838 Ops/s $\color{#d91a1a}-0.35\%$
test_td3_speed 7.9388ms 7.7845ms 128.4597 Ops/s 125.2771 Ops/s $\color{#35bf28}+2.54\%$
test_cql_speed 26.3487ms 25.1818ms 39.7112 Ops/s 39.4166 Ops/s $\color{#35bf28}+0.75\%$
test_a2c_speed 6.0430ms 5.6319ms 177.5593 Ops/s 178.5076 Ops/s $\color{#d91a1a}-0.53\%$
test_ppo_speed 7.0357ms 5.9419ms 168.2963 Ops/s 170.0729 Ops/s $\color{#d91a1a}-1.04\%$
test_reinforce_speed 4.8984ms 4.5650ms 219.0561 Ops/s 219.6177 Ops/s $\color{#d91a1a}-0.26\%$
test_iql_speed 20.3385ms 19.7231ms 50.7020 Ops/s 50.4461 Ops/s $\color{#35bf28}+0.51\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0844ms 2.8634ms 349.2295 Ops/s 341.8541 Ops/s $\color{#35bf28}+2.16\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7136ms 0.5369ms 1.8626 KOps/s 1.8513 KOps/s $\color{#35bf28}+0.61\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7600ms 0.5161ms 1.9375 KOps/s 1.9326 KOps/s $\color{#35bf28}+0.25\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1711ms 2.8889ms 346.1489 Ops/s 337.8559 Ops/s $\color{#35bf28}+2.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7057ms 0.5288ms 1.8912 KOps/s 1.8788 KOps/s $\color{#35bf28}+0.66\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.2318ms 0.5120ms 1.9529 KOps/s 1.9538 KOps/s $\color{#d91a1a}-0.04\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.5670ms 1.3903ms 719.2474 Ops/s 711.2989 Ops/s $\color{#35bf28}+1.12\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5372ms 1.3170ms 759.3189 Ops/s 744.7421 Ops/s $\color{#35bf28}+1.96\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.2859ms 2.9936ms 334.0430 Ops/s 326.3119 Ops/s $\color{#35bf28}+2.37\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3218ms 0.6613ms 1.5122 KOps/s 1.5041 KOps/s $\color{#35bf28}+0.54\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8625ms 0.6392ms 1.5644 KOps/s 1.5543 KOps/s $\color{#35bf28}+0.65\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0449ms 2.8572ms 349.9968 Ops/s 344.2263 Ops/s $\color{#35bf28}+1.68\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6919ms 0.5392ms 1.8547 KOps/s 1.8515 KOps/s $\color{#35bf28}+0.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.5374ms 0.5196ms 1.9246 KOps/s 1.9087 KOps/s $\color{#35bf28}+0.83\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1862ms 2.9029ms 344.4863 Ops/s 339.7673 Ops/s $\color{#35bf28}+1.39\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7444ms 0.5296ms 1.8882 KOps/s 1.8760 KOps/s $\color{#35bf28}+0.65\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6847ms 0.5102ms 1.9602 KOps/s 1.9397 KOps/s $\color{#35bf28}+1.06\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1648ms 2.9842ms 335.0931 Ops/s 326.5555 Ops/s $\color{#35bf28}+2.61\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3410ms 0.6633ms 1.5076 KOps/s 1.5088 KOps/s $\color{#d91a1a}-0.08\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8432ms 0.6391ms 1.5648 KOps/s 1.5483 KOps/s $\color{#35bf28}+1.06\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1304s 9.7162ms 102.9206 Ops/s 103.2316 Ops/s $\color{#d91a1a}-0.30\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.3290ms 13.8765ms 72.0641 Ops/s 68.5756 Ops/s $\textbf{\color{#35bf28}+5.09\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.2921ms 1.1068ms 903.4700 Ops/s 920.4236 Ops/s $\color{#d91a1a}-1.84\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1215s 7.1010ms 140.8243 Ops/s 140.1198 Ops/s $\color{#35bf28}+0.50\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.4343ms 13.8935ms 71.9759 Ops/s 69.2933 Ops/s $\color{#35bf28}+3.87\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.5177ms 1.1316ms 883.6841 Ops/s 887.7017 Ops/s $\color{#d91a1a}-0.45\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1235s 7.5051ms 133.2429 Ops/s 134.0852 Ops/s $\color{#d91a1a}-0.63\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1298s 16.5747ms 60.3328 Ops/s 57.2974 Ops/s $\textbf{\color{#35bf28}+5.30\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.6822ms 1.4530ms 688.2223 Ops/s 688.0407 Ops/s $\color{#35bf28}+0.03\%$

@vmoens vmoens merged commit fc8ccd9 into main Apr 18, 2024
62 of 67 checks passed
@vmoens vmoens deleted the fix-append_transform branch April 18, 2024 16:30
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
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
Development

Successfully merging this pull request may close these issues.

2 participants