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] Fit vecnorm out_keys #2157

Merged
merged 1 commit into from
May 10, 2024
Merged

[BugFix] Fit vecnorm out_keys #2157

merged 1 commit into from
May 10, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented May 10, 2024

No description provided.

Copy link

pytorch-bot bot commented May 10, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2157

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

❌ 1 New Failure, 14 Unrelated Failures

As of commit 53b33e8 with merge base be0747d (image):

NEW FAILURE - The following job has failed:

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

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 May 10, 2024
@vmoens vmoens added the bug Something isn't working label May 10, 2024
@vmoens vmoens merged commit 7befddc into main May 10, 2024
32 of 47 checks passed
@vmoens vmoens deleted the fix-vecnorm branch May 10, 2024 15:15
Copy link

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}4$. Worsened: $\large\color{#d91a1a}10$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 59.2763ms 58.5104ms 17.0910 Ops/s 17.2048 Ops/s $\color{#d91a1a}-0.66\%$
test_sync 40.8509ms 32.8200ms 30.4693 Ops/s 31.3091 Ops/s $\color{#d91a1a}-2.68\%$
test_async 54.1362ms 30.8567ms 32.4079 Ops/s 33.6912 Ops/s $\color{#d91a1a}-3.81\%$
test_simple 0.4641s 0.3870s 2.5838 Ops/s 2.7959 Ops/s $\textbf{\color{#d91a1a}-7.58\%}$
test_transformed 0.5389s 0.5367s 1.8634 Ops/s 1.8619 Ops/s $\color{#35bf28}+0.08\%$
test_serial 1.4032s 1.3169s 0.7593 Ops/s 0.7719 Ops/s $\color{#d91a1a}-1.63\%$
test_parallel 1.1902s 1.1413s 0.8762 Ops/s 0.9187 Ops/s $\color{#d91a1a}-4.62\%$
test_step_mdp_speed[True-True-True-True-True] 0.1680ms 22.6199μs 44.2088 KOps/s 43.9470 KOps/s $\color{#35bf28}+0.60\%$
test_step_mdp_speed[True-True-True-True-False] 50.7760μs 13.7877μs 72.5283 KOps/s 72.7703 KOps/s $\color{#d91a1a}-0.33\%$
test_step_mdp_speed[True-True-True-False-True] 44.2830μs 13.4732μs 74.2217 KOps/s 74.6933 KOps/s $\color{#d91a1a}-0.63\%$
test_step_mdp_speed[True-True-True-False-False] 37.8110μs 8.0709μs 123.9024 KOps/s 124.5684 KOps/s $\color{#d91a1a}-0.53\%$
test_step_mdp_speed[True-True-False-True-True] 59.8730μs 24.0836μs 41.5220 KOps/s 41.4110 KOps/s $\color{#35bf28}+0.27\%$
test_step_mdp_speed[True-True-False-True-False] 44.0730μs 15.0589μs 66.4059 KOps/s 66.6515 KOps/s $\color{#d91a1a}-0.37\%$
test_step_mdp_speed[True-True-False-False-True] 44.9350μs 14.4547μs 69.1818 KOps/s 69.4846 KOps/s $\color{#d91a1a}-0.44\%$
test_step_mdp_speed[True-True-False-False-False] 41.4080μs 9.2733μs 107.8364 KOps/s 106.7713 KOps/s $\color{#35bf28}+1.00\%$
test_step_mdp_speed[True-False-True-True-True] 61.0550μs 24.9755μs 40.0392 KOps/s 39.3108 KOps/s $\color{#35bf28}+1.85\%$
test_step_mdp_speed[True-False-True-True-False] 45.6470μs 16.5349μs 60.4782 KOps/s 60.6206 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[True-False-True-False-True] 61.9270μs 14.2387μs 70.2312 KOps/s 68.9464 KOps/s $\color{#35bf28}+1.86\%$
test_step_mdp_speed[True-False-True-False-False] 35.7880μs 9.1164μs 109.6920 KOps/s 106.1744 KOps/s $\color{#35bf28}+3.31\%$
test_step_mdp_speed[True-False-False-True-True] 60.9150μs 25.9289μs 38.5671 KOps/s 37.6396 KOps/s $\color{#35bf28}+2.46\%$
test_step_mdp_speed[True-False-False-True-False] 61.2260μs 17.4534μs 57.2955 KOps/s 57.5199 KOps/s $\color{#d91a1a}-0.39\%$
test_step_mdp_speed[True-False-False-False-True] 46.7380μs 15.4696μs 64.6429 KOps/s 64.6817 KOps/s $\color{#d91a1a}-0.06\%$
test_step_mdp_speed[True-False-False-False-False] 46.6270μs 10.4523μs 95.6729 KOps/s 96.2569 KOps/s $\color{#d91a1a}-0.61\%$
test_step_mdp_speed[False-True-True-True-True] 59.2910μs 24.7505μs 40.4031 KOps/s 40.0672 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[False-True-True-True-False] 53.2700μs 15.9335μs 62.7610 KOps/s 60.3480 KOps/s $\color{#35bf28}+4.00\%$
test_step_mdp_speed[False-True-True-False-True] 45.1250μs 16.4038μs 60.9616 KOps/s 60.9860 KOps/s $\color{#d91a1a}-0.04\%$
test_step_mdp_speed[False-True-True-False-False] 35.6770μs 10.3047μs 97.0428 KOps/s 95.6076 KOps/s $\color{#35bf28}+1.50\%$
test_step_mdp_speed[False-True-False-True-True] 56.6360μs 25.5977μs 39.0659 KOps/s 37.9474 KOps/s $\color{#35bf28}+2.95\%$
test_step_mdp_speed[False-True-False-True-False] 39.5940μs 17.2629μs 57.9278 KOps/s 56.1681 KOps/s $\color{#35bf28}+3.13\%$
test_step_mdp_speed[False-True-False-False-True] 56.5760μs 17.7177μs 56.4409 KOps/s 55.8620 KOps/s $\color{#35bf28}+1.04\%$
test_step_mdp_speed[False-True-False-False-False] 69.6810μs 11.5687μs 86.4400 KOps/s 82.9959 KOps/s $\color{#35bf28}+4.15\%$
test_step_mdp_speed[False-False-True-True-True] 59.0620μs 27.9685μs 35.7545 KOps/s 35.6464 KOps/s $\color{#35bf28}+0.30\%$
test_step_mdp_speed[False-False-True-True-False] 0.1051ms 18.9968μs 52.6404 KOps/s 51.4060 KOps/s $\color{#35bf28}+2.40\%$
test_step_mdp_speed[False-False-True-False-True] 52.3090μs 18.2202μs 54.8842 KOps/s 55.4840 KOps/s $\color{#d91a1a}-1.08\%$
test_step_mdp_speed[False-False-True-False-False] 52.3290μs 11.6658μs 85.7207 KOps/s 84.4935 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[False-False-False-True-True] 45.4060μs 29.2630μs 34.1728 KOps/s 33.3249 KOps/s $\color{#35bf28}+2.54\%$
test_step_mdp_speed[False-False-False-True-False] 61.5260μs 20.0944μs 49.7650 KOps/s 48.7130 KOps/s $\color{#35bf28}+2.16\%$
test_step_mdp_speed[False-False-False-False-True] 60.0020μs 19.0220μs 52.5707 KOps/s 52.7136 KOps/s $\color{#d91a1a}-0.27\%$
test_step_mdp_speed[False-False-False-False-False] 44.2930μs 12.7235μs 78.5946 KOps/s 76.4985 KOps/s $\color{#35bf28}+2.74\%$
test_values[generalized_advantage_estimate-True-True] 10.1323ms 9.8495ms 101.5280 Ops/s 96.9022 Ops/s $\color{#35bf28}+4.77\%$
test_values[vec_generalized_advantage_estimate-True-True] 38.5155ms 35.9458ms 27.8197 Ops/s 26.9763 Ops/s $\color{#35bf28}+3.13\%$
test_values[td0_return_estimate-False-False] 0.2520ms 0.1919ms 5.2101 KOps/s 4.7145 KOps/s $\textbf{\color{#35bf28}+10.51\%}$
test_values[td1_return_estimate-False-False] 27.7589ms 24.5128ms 40.7950 Ops/s 38.7724 Ops/s $\textbf{\color{#35bf28}+5.22\%}$
test_values[vec_td1_return_estimate-False-False] 37.8482ms 36.3098ms 27.5408 Ops/s 27.3776 Ops/s $\color{#35bf28}+0.60\%$
test_values[td_lambda_return_estimate-True-False] 36.6161ms 35.3252ms 28.3084 Ops/s 26.8133 Ops/s $\textbf{\color{#35bf28}+5.58\%}$
test_values[vec_td_lambda_return_estimate-True-False] 37.8037ms 36.2026ms 27.6223 Ops/s 27.1382 Ops/s $\color{#35bf28}+1.78\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.7519ms 8.4181ms 118.7917 Ops/s 114.2681 Ops/s $\color{#35bf28}+3.96\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.6758ms 2.1172ms 472.3233 Ops/s 461.0056 Ops/s $\color{#35bf28}+2.46\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4415ms 0.3691ms 2.7091 KOps/s 2.5697 KOps/s $\textbf{\color{#35bf28}+5.43\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 53.0762ms 48.9259ms 20.4391 Ops/s 19.8329 Ops/s $\color{#35bf28}+3.06\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.9784ms 3.2202ms 310.5419 Ops/s 297.1778 Ops/s $\color{#35bf28}+4.50\%$
test_dqn_speed 8.5567ms 1.4957ms 668.5974 Ops/s 678.8123 Ops/s $\color{#d91a1a}-1.50\%$
test_ddpg_speed 3.7960ms 3.0623ms 326.5570 Ops/s 318.1695 Ops/s $\color{#35bf28}+2.64\%$
test_sac_speed 10.7560ms 9.5214ms 105.0271 Ops/s 102.9216 Ops/s $\color{#35bf28}+2.05\%$
test_redq_speed 15.6767ms 14.8028ms 67.5547 Ops/s 66.9874 Ops/s $\color{#35bf28}+0.85\%$
test_redq_deprec_speed 17.4832ms 15.7115ms 63.6477 Ops/s 62.8580 Ops/s $\color{#35bf28}+1.26\%$
test_td3_speed 19.3467ms 9.4434ms 105.8944 Ops/s 104.5588 Ops/s $\color{#35bf28}+1.28\%$
test_cql_speed 42.6771ms 41.2629ms 24.2348 Ops/s 24.4542 Ops/s $\color{#d91a1a}-0.90\%$
test_a2c_speed 9.8239ms 8.6782ms 115.2318 Ops/s 118.9425 Ops/s $\color{#d91a1a}-3.12\%$
test_ppo_speed 10.4529ms 9.0505ms 110.4917 Ops/s 110.0661 Ops/s $\color{#35bf28}+0.39\%$
test_reinforce_speed 9.0866ms 7.6268ms 131.1168 Ops/s 136.1231 Ops/s $\color{#d91a1a}-3.68\%$
test_iql_speed 39.2151ms 37.1343ms 26.9293 Ops/s 27.6771 Ops/s $\color{#d91a1a}-2.70\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.0714ms 2.6979ms 370.6606 Ops/s 390.4522 Ops/s $\textbf{\color{#d91a1a}-5.07\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.1242s 0.6535ms 1.5303 KOps/s 1.8654 KOps/s $\textbf{\color{#d91a1a}-17.96\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8890ms 0.5677ms 1.7616 KOps/s 1.9299 KOps/s $\textbf{\color{#d91a1a}-8.72\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.0015ms 2.6441ms 378.2042 Ops/s 377.6621 Ops/s $\color{#35bf28}+0.14\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1559ms 0.5479ms 1.8252 KOps/s 1.8718 KOps/s $\color{#d91a1a}-2.49\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.9885ms 0.5188ms 1.9274 KOps/s 1.9591 KOps/s $\color{#d91a1a}-1.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.8831ms 1.3121ms 762.1122 Ops/s 785.5821 Ops/s $\color{#d91a1a}-2.99\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.7545ms 1.2236ms 817.2716 Ops/s 822.0878 Ops/s $\color{#d91a1a}-0.59\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.3722ms 2.8182ms 354.8357 Ops/s 364.5837 Ops/s $\color{#d91a1a}-2.67\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0396ms 0.6693ms 1.4941 KOps/s 1.4752 KOps/s $\color{#35bf28}+1.29\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8619ms 0.6410ms 1.5602 KOps/s 1.5609 KOps/s $\color{#d91a1a}-0.05\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.8695ms 2.6555ms 376.5777 Ops/s 371.0779 Ops/s $\color{#35bf28}+1.48\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1898ms 0.5526ms 1.8095 KOps/s 1.8164 KOps/s $\color{#d91a1a}-0.38\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8693ms 0.5347ms 1.8700 KOps/s 1.8745 KOps/s $\color{#d91a1a}-0.24\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1162ms 2.6762ms 373.6576 Ops/s 373.2193 Ops/s $\color{#35bf28}+0.12\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6990ms 0.5331ms 1.8757 KOps/s 1.8359 KOps/s $\color{#35bf28}+2.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.9181ms 0.5108ms 1.9577 KOps/s 1.9132 KOps/s $\color{#35bf28}+2.33\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.5651ms 2.8761ms 347.6914 Ops/s 371.1429 Ops/s $\textbf{\color{#d91a1a}-6.32\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3886ms 0.6801ms 1.4705 KOps/s 1.5093 KOps/s $\color{#d91a1a}-2.57\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.1263ms 0.6590ms 1.5174 KOps/s 1.5288 KOps/s $\color{#d91a1a}-0.75\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1420s 9.2902ms 107.6400 Ops/s 109.6129 Ops/s $\color{#d91a1a}-1.80\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.8356ms 14.2097ms 70.3747 Ops/s 72.2546 Ops/s $\color{#d91a1a}-2.60\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 4.6898ms 1.3566ms 737.1503 Ops/s 805.0523 Ops/s $\textbf{\color{#d91a1a}-8.43\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1418s 6.8186ms 146.6573 Ops/s 155.0156 Ops/s $\textbf{\color{#d91a1a}-5.39\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.4446ms 13.9733ms 71.5652 Ops/s 72.2846 Ops/s $\color{#d91a1a}-1.00\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.1192ms 1.3567ms 737.1020 Ops/s 800.4712 Ops/s $\textbf{\color{#d91a1a}-7.92\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1592s 10.4297ms 95.8804 Ops/s 104.3601 Ops/s $\textbf{\color{#d91a1a}-8.13\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.2225ms 14.7110ms 67.9766 Ops/s 70.8833 Ops/s $\color{#d91a1a}-4.10\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.0026ms 1.6706ms 598.5740 Ops/s 640.8835 Ops/s $\textbf{\color{#d91a1a}-6.60\%}$

Copy link

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1201s 0.1184s 8.4475 Ops/s 8.6157 Ops/s $\color{#d91a1a}-1.95\%$
test_sync 0.1017s 99.1690ms 10.0838 Ops/s 9.7009 Ops/s $\color{#35bf28}+3.95\%$
test_async 0.1915s 95.9879ms 10.4180 Ops/s 10.6360 Ops/s $\color{#d91a1a}-2.05\%$
test_single_pixels 0.1280s 0.1275s 7.8413 Ops/s 8.0063 Ops/s $\color{#d91a1a}-2.06\%$
test_sync_pixels 85.0651ms 80.8544ms 12.3679 Ops/s 12.3399 Ops/s $\color{#35bf28}+0.23\%$
test_async_pixels 0.1536s 77.2658ms 12.9423 Ops/s 14.6454 Ops/s $\textbf{\color{#d91a1a}-11.63\%}$
test_simple 0.8380s 0.7775s 1.2861 Ops/s 1.3081 Ops/s $\color{#d91a1a}-1.68\%$
test_transformed 1.0963s 1.0346s 0.9665 Ops/s 0.9963 Ops/s $\color{#d91a1a}-2.99\%$
test_serial 2.5234s 2.4530s 0.4077 Ops/s 0.4174 Ops/s $\color{#d91a1a}-2.33\%$
test_parallel 2.4485s 2.3284s 0.4295 Ops/s 0.4347 Ops/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[True-True-True-True-True] 99.1210μs 32.8905μs 30.4040 KOps/s 29.9613 KOps/s $\color{#35bf28}+1.48\%$
test_step_mdp_speed[True-True-True-True-False] 45.5500μs 19.5573μs 51.1317 KOps/s 50.5855 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[True-True-True-False-True] 46.4900μs 18.3725μs 54.4292 KOps/s 53.9623 KOps/s $\color{#35bf28}+0.87\%$
test_step_mdp_speed[True-True-True-False-False] 28.6610μs 11.1384μs 89.7795 KOps/s 89.6798 KOps/s $\color{#35bf28}+0.11\%$
test_step_mdp_speed[True-True-False-True-True] 51.9120μs 34.7201μs 28.8018 KOps/s 29.1333 KOps/s $\color{#d91a1a}-1.14\%$
test_step_mdp_speed[True-True-False-True-False] 35.5410μs 21.4607μs 46.5967 KOps/s 46.6954 KOps/s $\color{#d91a1a}-0.21\%$
test_step_mdp_speed[True-True-False-False-True] 39.4410μs 20.3434μs 49.1559 KOps/s 48.9693 KOps/s $\color{#35bf28}+0.38\%$
test_step_mdp_speed[True-True-False-False-False] 27.8300μs 12.8948μs 77.5504 KOps/s 76.8271 KOps/s $\color{#35bf28}+0.94\%$
test_step_mdp_speed[True-False-True-True-True] 98.9010μs 36.8017μs 27.1727 KOps/s 27.6548 KOps/s $\color{#d91a1a}-1.74\%$
test_step_mdp_speed[True-False-True-True-False] 41.1310μs 23.4163μs 42.7053 KOps/s 42.6433 KOps/s $\color{#35bf28}+0.15\%$
test_step_mdp_speed[True-False-True-False-True] 43.5210μs 20.4831μs 48.8206 KOps/s 48.9192 KOps/s $\color{#d91a1a}-0.20\%$
test_step_mdp_speed[True-False-True-False-False] 31.5010μs 12.9788μs 77.0488 KOps/s 76.8000 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[True-False-False-True-True] 53.7210μs 38.5268μs 25.9559 KOps/s 26.4793 KOps/s $\color{#d91a1a}-1.98\%$
test_step_mdp_speed[True-False-False-True-False] 51.5000μs 25.2393μs 39.6208 KOps/s 39.5831 KOps/s $\color{#35bf28}+0.10\%$
test_step_mdp_speed[True-False-False-False-True] 39.6000μs 22.1689μs 45.1082 KOps/s 45.3672 KOps/s $\color{#d91a1a}-0.57\%$
test_step_mdp_speed[True-False-False-False-False] 30.6700μs 14.8193μs 67.4793 KOps/s 68.0387 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[False-True-True-True-True] 54.2000μs 36.8514μs 27.1360 KOps/s 27.3518 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[False-True-True-True-False] 36.5400μs 23.4816μs 42.5865 KOps/s 41.9512 KOps/s $\color{#35bf28}+1.51\%$
test_step_mdp_speed[False-True-True-False-True] 44.2500μs 24.2168μs 41.2936 KOps/s 40.3148 KOps/s $\color{#35bf28}+2.43\%$
test_step_mdp_speed[False-True-True-False-False] 41.5700μs 15.0996μs 66.2268 KOps/s 66.2554 KOps/s $\color{#d91a1a}-0.04\%$
test_step_mdp_speed[False-True-False-True-True] 60.6410μs 38.0322μs 26.2935 KOps/s 25.8776 KOps/s $\color{#35bf28}+1.61\%$
test_step_mdp_speed[False-True-False-True-False] 50.8800μs 25.2445μs 39.6126 KOps/s 39.5753 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[False-True-False-False-True] 43.6100μs 26.0657μs 38.3646 KOps/s 37.8687 KOps/s $\color{#35bf28}+1.31\%$
test_step_mdp_speed[False-True-False-False-False] 41.1910μs 16.8625μs 59.3034 KOps/s 59.7227 KOps/s $\color{#d91a1a}-0.70\%$
test_step_mdp_speed[False-False-True-True-True] 70.5210μs 40.4476μs 24.7234 KOps/s 25.0493 KOps/s $\color{#d91a1a}-1.30\%$
test_step_mdp_speed[False-False-True-True-False] 40.8510μs 27.3356μs 36.5823 KOps/s 36.3635 KOps/s $\color{#35bf28}+0.60\%$
test_step_mdp_speed[False-False-True-False-True] 59.0810μs 26.1144μs 38.2931 KOps/s 37.8219 KOps/s $\color{#35bf28}+1.25\%$
test_step_mdp_speed[False-False-True-False-False] 37.6300μs 17.0665μs 58.5944 KOps/s 59.5739 KOps/s $\color{#d91a1a}-1.64\%$
test_step_mdp_speed[False-False-False-True-True] 63.8910μs 42.9747μs 23.2695 KOps/s 23.5278 KOps/s $\color{#d91a1a}-1.10\%$
test_step_mdp_speed[False-False-False-True-False] 49.9300μs 29.2753μs 34.1585 KOps/s 34.0019 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[False-False-False-False-True] 52.3410μs 28.0436μs 35.6588 KOps/s 35.2432 KOps/s $\color{#35bf28}+1.18\%$
test_step_mdp_speed[False-False-False-False-False] 33.5020μs 18.4041μs 54.3357 KOps/s 54.2482 KOps/s $\color{#35bf28}+0.16\%$
test_values[generalized_advantage_estimate-True-True] 26.2403ms 25.8252ms 38.7219 Ops/s 40.4462 Ops/s $\color{#d91a1a}-4.26\%$
test_values[vec_generalized_advantage_estimate-True-True] 81.3809ms 3.2017ms 312.3301 Ops/s 312.1888 Ops/s $\color{#35bf28}+0.05\%$
test_values[td0_return_estimate-False-False] 95.5110μs 65.9591μs 15.1609 KOps/s 15.6245 KOps/s $\color{#d91a1a}-2.97\%$
test_values[td1_return_estimate-False-False] 56.7143ms 55.1616ms 18.1286 Ops/s 18.9812 Ops/s $\color{#d91a1a}-4.49\%$
test_values[vec_td1_return_estimate-False-False] 2.0711ms 1.7725ms 564.1902 Ops/s 566.8564 Ops/s $\color{#d91a1a}-0.47\%$
test_values[td_lambda_return_estimate-True-False] 87.7728ms 86.9180ms 11.5051 Ops/s 11.8647 Ops/s $\color{#d91a1a}-3.03\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.1253ms 1.7738ms 563.7739 Ops/s 568.4981 Ops/s $\color{#d91a1a}-0.83\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.5222ms 24.4944ms 40.8257 Ops/s 43.0924 Ops/s $\textbf{\color{#d91a1a}-5.26\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8880ms 0.7123ms 1.4039 KOps/s 1.4387 KOps/s $\color{#d91a1a}-2.42\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7094ms 0.6603ms 1.5145 KOps/s 1.5443 KOps/s $\color{#d91a1a}-1.93\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5448ms 1.4624ms 683.7869 Ops/s 687.5547 Ops/s $\color{#d91a1a}-0.55\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9415ms 0.6790ms 1.4727 KOps/s 1.4931 KOps/s $\color{#d91a1a}-1.37\%$
test_dqn_speed 1.8237ms 1.4776ms 676.7797 Ops/s 710.7588 Ops/s $\color{#d91a1a}-4.78\%$
test_ddpg_speed 3.3071ms 2.9827ms 335.2703 Ops/s 350.9043 Ops/s $\color{#d91a1a}-4.46\%$
test_sac_speed 8.9470ms 8.5254ms 117.2965 Ops/s 120.4620 Ops/s $\color{#d91a1a}-2.63\%$
test_redq_speed 10.9969ms 10.3506ms 96.6130 Ops/s 90.9443 Ops/s $\textbf{\color{#35bf28}+6.23\%}$
test_redq_deprec_speed 11.9849ms 11.4485ms 87.3474 Ops/s 85.8581 Ops/s $\color{#35bf28}+1.73\%$
test_td3_speed 8.6235ms 8.4690ms 118.0770 Ops/s 120.3178 Ops/s $\color{#d91a1a}-1.86\%$
test_cql_speed 26.7652ms 25.9547ms 38.5286 Ops/s 40.0137 Ops/s $\color{#d91a1a}-3.71\%$
test_a2c_speed 5.9040ms 5.6457ms 177.1257 Ops/s 189.9736 Ops/s $\textbf{\color{#d91a1a}-6.76\%}$
test_ppo_speed 6.5605ms 5.9709ms 167.4794 Ops/s 179.9214 Ops/s $\textbf{\color{#d91a1a}-6.92\%}$
test_reinforce_speed 4.8810ms 4.6581ms 214.6815 Ops/s 235.3544 Ops/s $\textbf{\color{#d91a1a}-8.78\%}$
test_iql_speed 20.3770ms 19.8032ms 50.4969 Ops/s 52.9687 Ops/s $\color{#d91a1a}-4.67\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.8635ms 2.7916ms 358.2140 Ops/s 363.0413 Ops/s $\color{#d91a1a}-1.33\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8516ms 0.5934ms 1.6851 KOps/s 1.4929 KOps/s $\textbf{\color{#35bf28}+12.88\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 1.1192ms 0.5678ms 1.7612 KOps/s 1.7681 KOps/s $\color{#d91a1a}-0.39\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9652ms 2.8069ms 356.2641 Ops/s 359.3615 Ops/s $\color{#d91a1a}-0.86\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8358ms 0.5860ms 1.7065 KOps/s 1.7174 KOps/s $\color{#d91a1a}-0.64\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7311ms 0.5616ms 1.7806 KOps/s 1.7981 KOps/s $\color{#d91a1a}-0.97\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7941ms 1.5628ms 639.8608 Ops/s 661.4265 Ops/s $\color{#d91a1a}-3.26\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5908ms 1.4773ms 676.9160 Ops/s 693.5169 Ops/s $\color{#d91a1a}-2.39\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.9689ms 2.9226ms 342.1619 Ops/s 343.7203 Ops/s $\color{#d91a1a}-0.45\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9671ms 0.7259ms 1.3776 KOps/s 1.3954 KOps/s $\color{#d91a1a}-1.27\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.1155s 0.8012ms 1.2482 KOps/s 1.4322 KOps/s $\textbf{\color{#d91a1a}-12.85\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.8515ms 2.7995ms 357.2019 Ops/s 360.4735 Ops/s $\color{#d91a1a}-0.91\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7064ms 0.5973ms 1.6743 KOps/s 1.6937 KOps/s $\color{#d91a1a}-1.14\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.2888ms 0.5734ms 1.7440 KOps/s 1.7610 KOps/s $\color{#d91a1a}-0.96\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9302ms 2.8204ms 354.5632 Ops/s 358.7601 Ops/s $\color{#d91a1a}-1.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.1132s 0.7598ms 1.3161 KOps/s 1.7085 KOps/s $\textbf{\color{#d91a1a}-22.97\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7286ms 0.5653ms 1.7691 KOps/s 1.7852 KOps/s $\color{#d91a1a}-0.90\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.0763ms 2.9420ms 339.9087 Ops/s 345.4977 Ops/s $\color{#d91a1a}-1.62\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9785ms 0.7309ms 1.3682 KOps/s 1.3978 KOps/s $\color{#d91a1a}-2.11\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9027ms 0.7073ms 1.4137 KOps/s 1.4406 KOps/s $\color{#d91a1a}-1.87\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1190s 7.2396ms 138.1283 Ops/s 102.7997 Ops/s $\textbf{\color{#35bf28}+34.37\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 0.1258s 17.7859ms 56.2243 Ops/s 66.1964 Ops/s $\textbf{\color{#d91a1a}-15.06\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.3404ms 1.1757ms 850.5482 Ops/s 879.0246 Ops/s $\color{#d91a1a}-3.24\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1130s 7.0852ms 141.1387 Ops/s 139.5442 Ops/s $\color{#35bf28}+1.14\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.9615ms 15.6360ms 63.9550 Ops/s 65.8430 Ops/s $\color{#d91a1a}-2.87\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.6257ms 1.3138ms 761.1298 Ops/s 790.0304 Ops/s $\color{#d91a1a}-3.66\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1139s 7.4459ms 134.3024 Ops/s 134.1794 Ops/s $\color{#35bf28}+0.09\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.2670ms 15.7315ms 63.5668 Ops/s 64.9432 Ops/s $\color{#d91a1a}-2.12\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 3.1055ms 1.6839ms 593.8628 Ops/s 628.7282 Ops/s $\textbf{\color{#d91a1a}-5.55\%}$

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.

None yet

2 participants