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

[Refactor] Use filter_empty=False in apply for params #1882

Merged
merged 3 commits into from
Feb 6, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 6, 2024

No description provided.

Copy link

pytorch-bot bot commented Feb 6, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1882

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

✅ You can merge normally! (4 Unrelated Failures)

As of commit 2bb68e7 with merge base e53eb73 (image):

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 Feb 6, 2024
@vmoens vmoens added the Refactoring Refactoring of an existing feature label Feb 6, 2024
@vmoens vmoens changed the title [Refactor] Use filter_empty=True in apply for params [Refactor] Use filter_empty=False in apply for params Feb 6, 2024
Copy link

github-actions bot commented Feb 6, 2024

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}2$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1281s 66.5641ms 15.0231 Ops/s 16.1774 Ops/s $\textbf{\color{#d91a1a}-7.14\%}$
test_sync 53.2975ms 37.3006ms 26.8092 Ops/s 29.4406 Ops/s $\textbf{\color{#d91a1a}-8.94\%}$
test_async 50.4739ms 32.3245ms 30.9362 Ops/s 30.8720 Ops/s $\color{#35bf28}+0.21\%$
test_simple 0.4888s 0.4301s 2.3249 Ops/s 2.3163 Ops/s $\color{#35bf28}+0.37\%$
test_transformed 0.6522s 0.5953s 1.6799 Ops/s 1.6838 Ops/s $\color{#d91a1a}-0.23\%$
test_serial 1.4700s 1.4140s 0.7072 Ops/s 0.7069 Ops/s $\color{#35bf28}+0.04\%$
test_parallel 1.4573s 1.4033s 0.7126 Ops/s 0.7102 Ops/s $\color{#35bf28}+0.34\%$
test_step_mdp_speed[True-True-True-True-True] 0.1257ms 21.2596μs 47.0375 KOps/s 45.9885 KOps/s $\color{#35bf28}+2.28\%$
test_step_mdp_speed[True-True-True-True-False] 42.6590μs 13.0747μs 76.4838 KOps/s 75.7368 KOps/s $\color{#35bf28}+0.99\%$
test_step_mdp_speed[True-True-True-False-True] 38.8620μs 12.3375μs 81.0539 KOps/s 77.9450 KOps/s $\color{#35bf28}+3.99\%$
test_step_mdp_speed[True-True-True-False-False] 47.2980μs 7.6825μs 130.1667 KOps/s 129.3939 KOps/s $\color{#35bf28}+0.60\%$
test_step_mdp_speed[True-True-False-True-True] 63.5400μs 22.4430μs 44.5574 KOps/s 43.1206 KOps/s $\color{#35bf28}+3.33\%$
test_step_mdp_speed[True-True-False-True-False] 41.5780μs 14.3057μs 69.9023 KOps/s 68.7715 KOps/s $\color{#35bf28}+1.64\%$
test_step_mdp_speed[True-True-False-False-True] 47.5290μs 13.6403μs 73.3121 KOps/s 71.1930 KOps/s $\color{#35bf28}+2.98\%$
test_step_mdp_speed[True-True-False-False-False] 48.4810μs 8.8011μs 113.6217 KOps/s 111.6673 KOps/s $\color{#35bf28}+1.75\%$
test_step_mdp_speed[True-False-True-True-True] 67.4560μs 23.7328μs 42.1358 KOps/s 40.8809 KOps/s $\color{#35bf28}+3.07\%$
test_step_mdp_speed[True-False-True-True-False] 50.0230μs 15.6007μs 64.0998 KOps/s 63.0876 KOps/s $\color{#35bf28}+1.60\%$
test_step_mdp_speed[True-False-True-False-True] 45.4150μs 13.6264μs 73.3871 KOps/s 71.3593 KOps/s $\color{#35bf28}+2.84\%$
test_step_mdp_speed[True-False-True-False-False] 48.3110μs 8.8444μs 113.0656 KOps/s 111.1893 KOps/s $\color{#35bf28}+1.69\%$
test_step_mdp_speed[True-False-False-True-True] 59.5010μs 24.9952μs 40.0077 KOps/s 38.8310 KOps/s $\color{#35bf28}+3.03\%$
test_step_mdp_speed[True-False-False-True-False] 38.9230μs 16.8975μs 59.1802 KOps/s 58.3723 KOps/s $\color{#35bf28}+1.38\%$
test_step_mdp_speed[True-False-False-False-True] 36.4080μs 14.8334μs 67.4153 KOps/s 65.4629 KOps/s $\color{#35bf28}+2.98\%$
test_step_mdp_speed[True-False-False-False-False] 35.2850μs 10.1264μs 98.7519 KOps/s 97.9477 KOps/s $\color{#35bf28}+0.82\%$
test_step_mdp_speed[False-True-True-True-True] 50.0240μs 23.8188μs 41.9836 KOps/s 40.3412 KOps/s $\color{#35bf28}+4.07\%$
test_step_mdp_speed[False-True-True-True-False] 41.9990μs 15.7390μs 63.5366 KOps/s 61.8852 KOps/s $\color{#35bf28}+2.67\%$
test_step_mdp_speed[False-True-True-False-True] 48.4700μs 15.9614μs 62.6511 KOps/s 60.1061 KOps/s $\color{#35bf28}+4.23\%$
test_step_mdp_speed[False-True-True-False-False] 48.4400μs 10.0364μs 99.6373 KOps/s 97.6432 KOps/s $\color{#35bf28}+2.04\%$
test_step_mdp_speed[False-True-False-True-True] 49.4320μs 25.2134μs 39.6614 KOps/s 38.1591 KOps/s $\color{#35bf28}+3.94\%$
test_step_mdp_speed[False-True-False-True-False] 44.7740μs 16.7918μs 59.5528 KOps/s 58.4847 KOps/s $\color{#35bf28}+1.83\%$
test_step_mdp_speed[False-True-False-False-True] 42.8890μs 16.9491μs 59.0003 KOps/s 57.0727 KOps/s $\color{#35bf28}+3.38\%$
test_step_mdp_speed[False-True-False-False-False] 35.2760μs 11.2719μs 88.7161 KOps/s 87.0115 KOps/s $\color{#35bf28}+1.96\%$
test_step_mdp_speed[False-False-True-True-True] 90.2380μs 26.0656μs 38.3647 KOps/s 36.8704 KOps/s $\color{#35bf28}+4.05\%$
test_step_mdp_speed[False-False-True-True-False] 41.7480μs 18.1900μs 54.9753 KOps/s 54.6064 KOps/s $\color{#35bf28}+0.68\%$
test_step_mdp_speed[False-False-True-False-True] 42.2590μs 17.0041μs 58.8093 KOps/s 57.2376 KOps/s $\color{#35bf28}+2.75\%$
test_step_mdp_speed[False-False-True-False-False] 89.5840μs 11.4532μs 87.3115 KOps/s 87.7151 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[False-False-False-True-True] 0.1021ms 27.1509μs 36.8312 KOps/s 35.6340 KOps/s $\color{#35bf28}+3.36\%$
test_step_mdp_speed[False-False-False-True-False] 59.7410μs 19.1541μs 52.2081 KOps/s 51.3102 KOps/s $\color{#35bf28}+1.75\%$
test_step_mdp_speed[False-False-False-False-True] 62.4500μs 18.0698μs 55.3410 KOps/s 54.1430 KOps/s $\color{#35bf28}+2.21\%$
test_step_mdp_speed[False-False-False-False-False] 43.6680μs 12.3911μs 80.7033 KOps/s 79.7897 KOps/s $\color{#35bf28}+1.15\%$
test_values[generalized_advantage_estimate-True-True] 12.0560ms 9.3479ms 106.9757 Ops/s 107.1324 Ops/s $\color{#d91a1a}-0.15\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.5309ms 35.0873ms 28.5003 Ops/s 28.4236 Ops/s $\color{#35bf28}+0.27\%$
test_values[td0_return_estimate-False-False] 0.2344ms 0.1628ms 6.1435 KOps/s 6.0700 KOps/s $\color{#35bf28}+1.21\%$
test_values[td1_return_estimate-False-False] 23.5617ms 23.2996ms 42.9191 Ops/s 43.4374 Ops/s $\color{#d91a1a}-1.19\%$
test_values[vec_td1_return_estimate-False-False] 36.7567ms 35.4336ms 28.2218 Ops/s 28.1136 Ops/s $\color{#35bf28}+0.38\%$
test_values[td_lambda_return_estimate-True-False] 36.8415ms 33.9668ms 29.4405 Ops/s 30.0811 Ops/s $\color{#d91a1a}-2.13\%$
test_values[vec_td_lambda_return_estimate-True-False] 36.3667ms 35.1921ms 28.4155 Ops/s 28.1961 Ops/s $\color{#35bf28}+0.78\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.1533ms 8.0492ms 124.2355 Ops/s 121.7241 Ops/s $\color{#35bf28}+2.06\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4277ms 1.9666ms 508.4930 Ops/s 509.5299 Ops/s $\color{#d91a1a}-0.20\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5460ms 0.3502ms 2.8552 KOps/s 2.8943 KOps/s $\color{#d91a1a}-1.35\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 49.3851ms 46.2573ms 21.6182 Ops/s 21.9137 Ops/s $\color{#d91a1a}-1.35\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.7277ms 3.0112ms 332.0901 Ops/s 332.5866 Ops/s $\color{#d91a1a}-0.15\%$
test_dqn_speed 12.7880ms 5.9781ms 167.2779 Ops/s 157.9498 Ops/s $\textbf{\color{#35bf28}+5.91\%}$
test_ddpg_speed 13.6796ms 11.7335ms 85.2259 Ops/s 87.0525 Ops/s $\color{#d91a1a}-2.10\%$
test_sac_speed 26.3342ms 23.8277ms 41.9680 Ops/s 43.0570 Ops/s $\color{#d91a1a}-2.53\%$
test_redq_speed 15.7895ms 13.9576ms 71.6456 Ops/s 70.5613 Ops/s $\color{#35bf28}+1.54\%$
test_redq_deprec_speed 22.3345ms 21.6235ms 46.2461 Ops/s 46.5349 Ops/s $\color{#d91a1a}-0.62\%$
test_td3_speed 25.2626ms 16.6831ms 59.9410 Ops/s 61.3623 Ops/s $\color{#d91a1a}-2.32\%$
test_cql_speed 75.4951ms 74.0589ms 13.5028 Ops/s 13.5803 Ops/s $\color{#d91a1a}-0.57\%$
test_a2c_speed 23.3502ms 22.0417ms 45.3685 Ops/s 45.6002 Ops/s $\color{#d91a1a}-0.51\%$
test_ppo_speed 23.6527ms 22.2319ms 44.9805 Ops/s 45.3522 Ops/s $\color{#d91a1a}-0.82\%$
test_reinforce_speed 23.2356ms 21.1902ms 47.1916 Ops/s 47.5387 Ops/s $\color{#d91a1a}-0.73\%$
test_iql_speed 56.2818ms 55.6891ms 17.9568 Ops/s 18.1266 Ops/s $\color{#d91a1a}-0.94\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.8560ms 2.5741ms 388.4844 Ops/s 381.7969 Ops/s $\color{#35bf28}+1.75\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7925ms 0.4956ms 2.0178 KOps/s 1.9997 KOps/s $\color{#35bf28}+0.91\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8334ms 0.4990ms 2.0039 KOps/s 2.1325 KOps/s $\textbf{\color{#d91a1a}-6.03\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8453ms 2.5346ms 394.5447 Ops/s 389.2951 Ops/s $\color{#35bf28}+1.35\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7780ms 0.4910ms 2.0367 KOps/s 2.0330 KOps/s $\color{#35bf28}+0.18\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7774ms 0.4656ms 2.1476 KOps/s 2.1418 KOps/s $\color{#35bf28}+0.27\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.6394ms 2.3434ms 426.7250 Ops/s 421.3179 Ops/s $\color{#35bf28}+1.28\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7146ms 0.6061ms 1.6500 KOps/s 1.6287 KOps/s $\color{#35bf28}+1.31\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7819ms 0.5812ms 1.7205 KOps/s 1.7197 KOps/s $\color{#35bf28}+0.04\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.9340ms 2.5784ms 387.8413 Ops/s 373.4142 Ops/s $\color{#35bf28}+3.86\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8195ms 0.4988ms 2.0048 KOps/s 1.9868 KOps/s $\color{#35bf28}+0.91\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5588ms 0.4695ms 2.1300 KOps/s 2.1281 KOps/s $\color{#35bf28}+0.09\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9355ms 2.6038ms 384.0491 Ops/s 384.8575 Ops/s $\color{#d91a1a}-0.21\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8657ms 0.4935ms 2.0262 KOps/s 2.0168 KOps/s $\color{#35bf28}+0.47\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7185ms 0.4666ms 2.1433 KOps/s 2.1411 KOps/s $\color{#35bf28}+0.10\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.5698ms 2.3836ms 419.5298 Ops/s 408.1382 Ops/s $\color{#35bf28}+2.79\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1221ms 0.6180ms 1.6181 KOps/s 1.6116 KOps/s $\color{#35bf28}+0.40\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9714ms 0.5871ms 1.7033 KOps/s 1.6980 KOps/s $\color{#35bf28}+0.32\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 98.9394ms 9.7717ms 102.3360 Ops/s 131.2778 Ops/s $\textbf{\color{#d91a1a}-22.05\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.1373ms 13.2220ms 75.6314 Ops/s 75.1691 Ops/s $\color{#35bf28}+0.61\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 4.2733ms 2.5107ms 398.2953 Ops/s 400.0337 Ops/s $\color{#d91a1a}-0.43\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 99.3703ms 9.7391ms 102.6788 Ops/s 104.7513 Ops/s $\color{#d91a1a}-1.98\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.2387ms 13.2659ms 75.3811 Ops/s 75.8913 Ops/s $\color{#d91a1a}-0.67\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.9442ms 2.5484ms 392.4098 Ops/s 396.5255 Ops/s $\color{#d91a1a}-1.04\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 97.1207ms 7.9989ms 125.0177 Ops/s 125.3772 Ops/s $\color{#d91a1a}-0.29\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 15.6115ms 13.3766ms 74.7572 Ops/s 65.6636 Ops/s $\textbf{\color{#35bf28}+13.85\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.9831ms 2.7110ms 368.8677 Ops/s 371.3813 Ops/s $\color{#d91a1a}-0.68\%$

Copy link

github-actions bot commented Feb 6, 2024

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1175s 0.1166s 8.5727 Ops/s 8.4891 Ops/s $\color{#35bf28}+0.98\%$
test_sync 95.6636ms 95.4589ms 10.4757 Ops/s 10.4090 Ops/s $\color{#35bf28}+0.64\%$
test_async 0.2530s 91.7237ms 10.9023 Ops/s 10.8320 Ops/s $\color{#35bf28}+0.65\%$
test_single_pixels 0.1389s 0.1386s 7.2139 Ops/s 7.1666 Ops/s $\color{#35bf28}+0.66\%$
test_sync_pixels 83.9133ms 82.6409ms 12.1005 Ops/s 11.7185 Ops/s $\color{#35bf28}+3.26\%$
test_async_pixels 0.1455s 74.1120ms 13.4931 Ops/s 13.2814 Ops/s $\color{#35bf28}+1.59\%$
test_simple 0.9312s 0.8457s 1.1825 Ops/s 1.1886 Ops/s $\color{#d91a1a}-0.52\%$
test_transformed 1.1584s 1.0965s 0.9120 Ops/s 0.9139 Ops/s $\color{#d91a1a}-0.21\%$
test_serial 2.4376s 2.4357s 0.4106 Ops/s 0.4117 Ops/s $\color{#d91a1a}-0.27\%$
test_parallel 2.1853s 2.1211s 0.4715 Ops/s 0.4689 Ops/s $\color{#35bf28}+0.54\%$
test_step_mdp_speed[True-True-True-True-True] 75.3120μs 32.7005μs 30.5806 KOps/s 30.6243 KOps/s $\color{#d91a1a}-0.14\%$
test_step_mdp_speed[True-True-True-True-False] 44.0300μs 19.5061μs 51.2661 KOps/s 50.5532 KOps/s $\color{#35bf28}+1.41\%$
test_step_mdp_speed[True-True-True-False-True] 46.3810μs 18.4700μs 54.1418 KOps/s 54.4930 KOps/s $\color{#d91a1a}-0.64\%$
test_step_mdp_speed[True-True-True-False-False] 29.8300μs 11.1814μs 89.4341 KOps/s 89.1044 KOps/s $\color{#35bf28}+0.37\%$
test_step_mdp_speed[True-True-False-True-True] 75.6420μs 34.3703μs 29.0949 KOps/s 29.2553 KOps/s $\color{#d91a1a}-0.55\%$
test_step_mdp_speed[True-True-False-True-False] 44.4110μs 21.3588μs 46.8191 KOps/s 47.1917 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-True-False-False-True] 48.9000μs 20.3677μs 49.0973 KOps/s 49.5681 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[True-True-False-False-False] 36.2000μs 13.0724μs 76.4969 KOps/s 76.7234 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[True-False-True-True-True] 60.0510μs 36.6953μs 27.2515 KOps/s 27.3981 KOps/s $\color{#d91a1a}-0.54\%$
test_step_mdp_speed[True-False-True-True-False] 52.1410μs 23.4076μs 42.7212 KOps/s 42.4389 KOps/s $\color{#35bf28}+0.67\%$
test_step_mdp_speed[True-False-True-False-True] 58.7210μs 20.2839μs 49.3001 KOps/s 49.4151 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[True-False-True-False-False] 44.6910μs 13.1227μs 76.2041 KOps/s 76.1711 KOps/s $\color{#35bf28}+0.04\%$
test_step_mdp_speed[True-False-False-True-True] 71.6310μs 38.3533μs 26.0733 KOps/s 26.1536 KOps/s $\color{#d91a1a}-0.31\%$
test_step_mdp_speed[True-False-False-True-False] 47.1210μs 25.3908μs 39.3844 KOps/s 39.9624 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[True-False-False-False-True] 45.6500μs 21.8376μs 45.7926 KOps/s 45.0201 KOps/s $\color{#35bf28}+1.72\%$
test_step_mdp_speed[True-False-False-False-False] 37.3210μs 14.7278μs 67.8987 KOps/s 66.9510 KOps/s $\color{#35bf28}+1.42\%$
test_step_mdp_speed[False-True-True-True-True] 59.1510μs 35.8035μs 27.9302 KOps/s 27.4235 KOps/s $\color{#35bf28}+1.85\%$
test_step_mdp_speed[False-True-True-True-False] 42.5400μs 23.5963μs 42.3795 KOps/s 42.9423 KOps/s $\color{#d91a1a}-1.31\%$
test_step_mdp_speed[False-True-True-False-True] 74.2510μs 24.2359μs 41.2611 KOps/s 40.7524 KOps/s $\color{#35bf28}+1.25\%$
test_step_mdp_speed[False-True-True-False-False] 38.8500μs 15.1150μs 66.1596 KOps/s 66.8712 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-True-False-True-True] 74.3510μs 38.2228μs 26.1624 KOps/s 26.1882 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[False-True-False-True-False] 50.6000μs 25.3936μs 39.3800 KOps/s 39.2189 KOps/s $\color{#35bf28}+0.41\%$
test_step_mdp_speed[False-True-False-False-True] 47.6510μs 25.9746μs 38.4991 KOps/s 38.3098 KOps/s $\color{#35bf28}+0.49\%$
test_step_mdp_speed[False-True-False-False-False] 45.8110μs 16.8944μs 59.1912 KOps/s 59.8451 KOps/s $\color{#d91a1a}-1.09\%$
test_step_mdp_speed[False-False-True-True-True] 70.7810μs 40.2739μs 24.8300 KOps/s 25.1562 KOps/s $\color{#d91a1a}-1.30\%$
test_step_mdp_speed[False-False-True-True-False] 69.9510μs 27.5701μs 36.2712 KOps/s 36.2646 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[False-False-True-False-True] 58.5510μs 26.3056μs 38.0147 KOps/s 38.3590 KOps/s $\color{#d91a1a}-0.90\%$
test_step_mdp_speed[False-False-True-False-False] 52.8910μs 16.7962μs 59.5374 KOps/s 59.2075 KOps/s $\color{#35bf28}+0.56\%$
test_step_mdp_speed[False-False-False-True-True] 64.9310μs 41.8487μs 23.8956 KOps/s 24.0746 KOps/s $\color{#d91a1a}-0.74\%$
test_step_mdp_speed[False-False-False-True-False] 67.3210μs 29.4240μs 33.9858 KOps/s 34.0803 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[False-False-False-False-True] 49.5900μs 27.7060μs 36.0933 KOps/s 35.4905 KOps/s $\color{#35bf28}+1.70\%$
test_step_mdp_speed[False-False-False-False-False] 47.8500μs 18.7192μs 53.4210 KOps/s 53.6813 KOps/s $\color{#d91a1a}-0.48\%$
test_values[generalized_advantage_estimate-True-True] 25.2437ms 24.6170ms 40.6223 Ops/s 39.9393 Ops/s $\color{#35bf28}+1.71\%$
test_values[vec_generalized_advantage_estimate-True-True] 83.6708ms 3.2386ms 308.7708 Ops/s 304.1874 Ops/s $\color{#35bf28}+1.51\%$
test_values[td0_return_estimate-False-False] 95.7110μs 60.8320μs 16.4387 KOps/s 16.1699 KOps/s $\color{#35bf28}+1.66\%$
test_values[td1_return_estimate-False-False] 53.3824ms 52.9637ms 18.8809 Ops/s 18.5077 Ops/s $\color{#35bf28}+2.02\%$
test_values[vec_td1_return_estimate-False-False] 2.0169ms 1.7614ms 567.7208 Ops/s 564.7171 Ops/s $\color{#35bf28}+0.53\%$
test_values[td_lambda_return_estimate-True-False] 84.8667ms 84.5392ms 11.8288 Ops/s 11.6149 Ops/s $\color{#35bf28}+1.84\%$
test_values[vec_td_lambda_return_estimate-True-False] 3.9532ms 1.7995ms 555.7242 Ops/s 552.3298 Ops/s $\color{#35bf28}+0.61\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.7773ms 23.5794ms 42.4099 Ops/s 41.7600 Ops/s $\color{#35bf28}+1.56\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8663ms 0.7018ms 1.4248 KOps/s 1.4078 KOps/s $\color{#35bf28}+1.21\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7079ms 0.6578ms 1.5203 KOps/s 1.5131 KOps/s $\color{#35bf28}+0.48\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.4931ms 1.4547ms 687.4330 Ops/s 684.6932 Ops/s $\color{#35bf28}+0.40\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9631ms 0.6750ms 1.4814 KOps/s 1.4788 KOps/s $\color{#35bf28}+0.17\%$
test_dqn_speed 14.0707ms 7.6338ms 130.9957 Ops/s 135.0021 Ops/s $\color{#d91a1a}-2.97\%$
test_ddpg_speed 15.3057ms 14.3815ms 69.5338 Ops/s 69.8568 Ops/s $\color{#d91a1a}-0.46\%$
test_sac_speed 29.3296ms 28.6923ms 34.8526 Ops/s 35.4937 Ops/s $\color{#d91a1a}-1.81\%$
test_redq_speed 0.1002s 12.5263ms 79.8323 Ops/s 86.4987 Ops/s $\textbf{\color{#d91a1a}-7.71\%}$
test_redq_deprec_speed 23.7877ms 23.0447ms 43.3940 Ops/s 44.2214 Ops/s $\color{#d91a1a}-1.87\%$
test_td3_speed 29.0921ms 19.1909ms 52.1079 Ops/s 52.7818 Ops/s $\color{#d91a1a}-1.28\%$
test_cql_speed 76.2928ms 75.5481ms 13.2366 Ops/s 13.4367 Ops/s $\color{#d91a1a}-1.49\%$
test_a2c_speed 26.4624ms 25.2954ms 39.5328 Ops/s 40.0603 Ops/s $\color{#d91a1a}-1.32\%$
test_ppo_speed 26.8591ms 25.5651ms 39.1159 Ops/s 39.7212 Ops/s $\color{#d91a1a}-1.52\%$
test_reinforce_speed 25.1621ms 24.4008ms 40.9822 Ops/s 41.8051 Ops/s $\color{#d91a1a}-1.97\%$
test_iql_speed 51.4390ms 50.4796ms 19.8100 Ops/s 19.9538 Ops/s $\color{#d91a1a}-0.72\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.6481ms 3.5534ms 281.4222 Ops/s 278.5635 Ops/s $\color{#35bf28}+1.03\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6761ms 0.5526ms 1.8097 KOps/s 1.8106 KOps/s $\color{#d91a1a}-0.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6566ms 0.5243ms 1.9074 KOps/s 1.9076 KOps/s $\color{#d91a1a}-0.01\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.7450ms 3.5979ms 277.9387 Ops/s 278.6272 Ops/s $\color{#d91a1a}-0.25\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6851ms 0.5490ms 1.8216 KOps/s 1.8248 KOps/s $\color{#d91a1a}-0.17\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6674ms 0.5248ms 1.9056 KOps/s 1.9179 KOps/s $\color{#d91a1a}-0.64\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.3699ms 3.2956ms 303.4368 Ops/s 304.9777 Ops/s $\color{#d91a1a}-0.51\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8140ms 0.6733ms 1.4853 KOps/s 1.4716 KOps/s $\color{#35bf28}+0.93\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7964ms 0.6457ms 1.5488 KOps/s 1.5355 KOps/s $\color{#35bf28}+0.86\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.6930ms 3.6097ms 277.0328 Ops/s 279.9590 Ops/s $\color{#d91a1a}-1.05\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6919ms 0.5521ms 1.8113 KOps/s 1.8074 KOps/s $\color{#35bf28}+0.22\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6918ms 0.5241ms 1.9081 KOps/s 1.8922 KOps/s $\color{#35bf28}+0.84\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.7734ms 3.6208ms 276.1842 Ops/s 277.1045 Ops/s $\color{#d91a1a}-0.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6933ms 0.5433ms 1.8406 KOps/s 1.8231 KOps/s $\color{#35bf28}+0.96\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6640ms 0.5207ms 1.9204 KOps/s 1.9117 KOps/s $\color{#35bf28}+0.45\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.3974ms 3.3023ms 302.8221 Ops/s 300.7353 Ops/s $\color{#35bf28}+0.69\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8334ms 0.6745ms 1.4827 KOps/s 1.4784 KOps/s $\color{#35bf28}+0.29\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8066ms 0.6524ms 1.5329 KOps/s 1.5396 KOps/s $\color{#d91a1a}-0.44\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1250s 10.1407ms 98.6125 Ops/s 100.6210 Ops/s $\color{#d91a1a}-2.00\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 18.4636ms 16.2370ms 61.5877 Ops/s 60.5229 Ops/s $\color{#35bf28}+1.76\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.3857ms 3.0604ms 326.7561 Ops/s 326.1193 Ops/s $\color{#35bf28}+0.20\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1191s 12.2318ms 81.7541 Ops/s 98.3987 Ops/s $\textbf{\color{#d91a1a}-16.92\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 18.3169ms 16.2960ms 61.3646 Ops/s 61.0336 Ops/s $\color{#35bf28}+0.54\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.6799ms 3.0620ms 326.5856 Ops/s 325.7935 Ops/s $\color{#35bf28}+0.24\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1197s 10.3121ms 96.9730 Ops/s 97.1191 Ops/s $\color{#d91a1a}-0.15\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.9546ms 16.5341ms 60.4812 Ops/s 53.1097 Ops/s $\textbf{\color{#35bf28}+13.88\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.7596ms 3.2993ms 303.0931 Ops/s 305.5221 Ops/s $\color{#d91a1a}-0.80\%$

@vmoens vmoens merged commit 1fe745a into main Feb 6, 2024
64 of 68 checks passed
@vmoens vmoens deleted the somemore-filter-empty branch February 6, 2024 18:31
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Refactoring Refactoring of an existing feature
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants