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

[Refactor] Refactor split_trajectories #1955

Merged
merged 2 commits into from
Feb 23, 2024
Merged

[Refactor] Refactor split_trajectories #1955

merged 2 commits into from
Feb 23, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 23, 2024 •
edited
Loading

No description provided.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Feb 23, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1955

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

❌ 3 New Failures, 1 Unrelated Failure

As of commit 2322b5f with merge base 15876b8 (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 Feb 23, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 23, 2024 •
edited
Loading

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}10$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 65.4774ms 62.8731ms 15.9050 Ops/s 16.5059 Ops/s $\color{#d91a1a}-3.64\%$
test_sync 40.3006ms 33.8256ms 29.5634 Ops/s 29.0752 Ops/s $\color{#35bf28}+1.68\%$
test_async 69.8586ms 30.3391ms 32.9608 Ops/s 31.7305 Ops/s $\color{#35bf28}+3.88\%$
test_simple 0.5013s 0.4499s 2.2228 Ops/s 2.2852 Ops/s $\color{#d91a1a}-2.73\%$
test_transformed 0.6537s 0.6073s 1.6467 Ops/s 1.6869 Ops/s $\color{#d91a1a}-2.38\%$
test_serial 1.5444s 1.4788s 0.6762 Ops/s 0.6944 Ops/s $\color{#d91a1a}-2.62\%$
test_parallel 1.5026s 1.4483s 0.6905 Ops/s 0.7019 Ops/s $\color{#d91a1a}-1.63\%$
test_step_mdp_speed[True-True-True-True-True] 0.1427ms 21.3334μs 46.8748 KOps/s 47.2642 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[True-True-True-True-False] 39.0130μs 13.0061μs 76.8870 KOps/s 77.7733 KOps/s $\color{#d91a1a}-1.14\%$
test_step_mdp_speed[True-True-True-False-True] 33.8730μs 12.4557μs 80.2848 KOps/s 81.2706 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[True-True-True-False-False] 30.4470μs 7.5395μs 132.6343 KOps/s 134.5651 KOps/s $\color{#d91a1a}-1.43\%$
test_step_mdp_speed[True-True-False-True-True] 67.2450μs 22.7490μs 43.9580 KOps/s 44.6723 KOps/s $\color{#d91a1a}-1.60\%$
test_step_mdp_speed[True-True-False-True-False] 44.4330μs 14.2347μs 70.2506 KOps/s 71.1517 KOps/s $\color{#d91a1a}-1.27\%$
test_step_mdp_speed[True-True-False-False-True] 44.3430μs 13.7207μs 72.8828 KOps/s 74.5240 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[True-True-False-False-False] 32.9210μs 8.8024μs 113.6057 KOps/s 113.9046 KOps/s $\color{#d91a1a}-0.26\%$
test_step_mdp_speed[True-False-True-True-True] 58.4290μs 24.0163μs 41.6385 KOps/s 41.7053 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[True-False-True-True-False] 40.7860μs 15.4873μs 64.5691 KOps/s 65.2566 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[True-False-True-False-True] 39.2630μs 13.6797μs 73.1009 KOps/s 73.3864 KOps/s $\color{#d91a1a}-0.39\%$
test_step_mdp_speed[True-False-True-False-False] 26.5890μs 8.8487μs 113.0114 KOps/s 115.8326 KOps/s $\color{#d91a1a}-2.44\%$
test_step_mdp_speed[True-False-False-True-True] 89.0890μs 24.9304μs 40.1117 KOps/s 40.1527 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[True-False-False-True-False] 47.8890μs 16.8217μs 59.4469 KOps/s 60.6000 KOps/s $\color{#d91a1a}-1.90\%$
test_step_mdp_speed[True-False-False-False-True] 48.9710μs 14.8093μs 67.5252 KOps/s 68.3782 KOps/s $\color{#d91a1a}-1.25\%$
test_step_mdp_speed[True-False-False-False-False] 36.7580μs 9.9763μs 100.2374 KOps/s 101.5615 KOps/s $\color{#d91a1a}-1.30\%$
test_step_mdp_speed[False-True-True-True-True] 77.8650μs 24.0687μs 41.5478 KOps/s 42.0732 KOps/s $\color{#d91a1a}-1.25\%$
test_step_mdp_speed[False-True-True-True-False] 45.6250μs 15.6290μs 63.9836 KOps/s 65.2467 KOps/s $\color{#d91a1a}-1.94\%$
test_step_mdp_speed[False-True-True-False-True] 51.2160μs 15.9485μs 62.7017 KOps/s 63.6802 KOps/s $\color{#d91a1a}-1.54\%$
test_step_mdp_speed[False-True-True-False-False] 32.0300μs 10.0027μs 99.9728 KOps/s 101.5352 KOps/s $\color{#d91a1a}-1.54\%$
test_step_mdp_speed[False-True-False-True-True] 48.1490μs 25.5512μs 39.1372 KOps/s 40.1693 KOps/s $\color{#d91a1a}-2.57\%$
test_step_mdp_speed[False-True-False-True-False] 42.7300μs 16.6800μs 59.9522 KOps/s 60.5858 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[False-True-False-False-True] 50.5140μs 17.2314μs 58.0335 KOps/s 59.3325 KOps/s $\color{#d91a1a}-2.19\%$
test_step_mdp_speed[False-True-False-False-False] 35.1760μs 11.1798μs 89.4468 KOps/s 90.3751 KOps/s $\color{#d91a1a}-1.03\%$
test_step_mdp_speed[False-False-True-True-True] 62.0450μs 26.2702μs 38.0659 KOps/s 38.1018 KOps/s $\color{#d91a1a}-0.09\%$
test_step_mdp_speed[False-False-True-True-False] 45.9950μs 18.0318μs 55.4577 KOps/s 55.9953 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[False-False-True-False-True] 53.3400μs 17.1348μs 58.3607 KOps/s 59.1279 KOps/s $\color{#d91a1a}-1.30\%$
test_step_mdp_speed[False-False-True-False-False] 35.9770μs 11.2175μs 89.1468 KOps/s 90.0982 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-False-False-True-True] 75.0390μs 27.2126μs 36.7476 KOps/s 36.7392 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[False-False-False-True-False] 57.2960μs 19.0888μs 52.3868 KOps/s 53.3989 KOps/s $\color{#d91a1a}-1.90\%$
test_step_mdp_speed[False-False-False-False-True] 40.0850μs 18.1600μs 55.0662 KOps/s 55.8568 KOps/s $\color{#d91a1a}-1.42\%$
test_step_mdp_speed[False-False-False-False-False] 46.0560μs 12.2856μs 81.3962 KOps/s 82.2454 KOps/s $\color{#d91a1a}-1.03\%$
test_values[generalized_advantage_estimate-True-True] 9.8598ms 9.0427ms 110.5870 Ops/s 105.4173 Ops/s $\color{#35bf28}+4.90\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.6097ms 33.3411ms 29.9930 Ops/s 28.1672 Ops/s $\textbf{\color{#35bf28}+6.48\%}$
test_values[td0_return_estimate-False-False] 0.2180ms 0.1755ms 5.6969 KOps/s 5.7204 KOps/s $\color{#d91a1a}-0.41\%$
test_values[td1_return_estimate-False-False] 25.3428ms 23.1265ms 43.2405 Ops/s 41.6623 Ops/s $\color{#35bf28}+3.79\%$
test_values[vec_td1_return_estimate-False-False] 49.9035ms 34.0625ms 29.3578 Ops/s 27.8120 Ops/s $\textbf{\color{#35bf28}+5.56\%}$
test_values[td_lambda_return_estimate-True-False] 36.1461ms 33.3152ms 30.0164 Ops/s 29.0405 Ops/s $\color{#35bf28}+3.36\%$
test_values[vec_td_lambda_return_estimate-True-False] 34.7620ms 33.5113ms 29.8406 Ops/s 27.1542 Ops/s $\textbf{\color{#35bf28}+9.89\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 9.5315ms 7.9112ms 126.4034 Ops/s 120.9541 Ops/s $\color{#35bf28}+4.51\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.5104ms 2.0558ms 486.4394 Ops/s 493.8385 Ops/s $\color{#d91a1a}-1.50\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4792ms 0.3557ms 2.8117 KOps/s 2.8667 KOps/s $\color{#d91a1a}-1.92\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 43.2691ms 41.6790ms 23.9929 Ops/s 21.7739 Ops/s $\textbf{\color{#35bf28}+10.19\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.6084ms 3.0144ms 331.7449 Ops/s 323.8568 Ops/s $\color{#35bf28}+2.44\%$
test_dqn_speed 72.6644ms 1.5348ms 651.5335 Ops/s 694.1582 Ops/s $\textbf{\color{#d91a1a}-6.14\%}$
test_ddpg_speed 3.3076ms 2.8115ms 355.6809 Ops/s 325.1813 Ops/s $\textbf{\color{#35bf28}+9.38\%}$
test_sac_speed 9.9034ms 8.5714ms 116.6672 Ops/s 117.8498 Ops/s $\color{#d91a1a}-1.00\%$
test_redq_speed 14.2409ms 13.4228ms 74.5000 Ops/s 75.3607 Ops/s $\color{#d91a1a}-1.14\%$
test_redq_deprec_speed 15.4600ms 13.6214ms 73.4141 Ops/s 72.2560 Ops/s $\color{#35bf28}+1.60\%$
test_td3_speed 8.7596ms 8.4713ms 118.0459 Ops/s 117.5974 Ops/s $\color{#35bf28}+0.38\%$
test_cql_speed 37.1273ms 36.1784ms 27.6408 Ops/s 27.2465 Ops/s $\color{#35bf28}+1.45\%$
test_a2c_speed 8.5929ms 7.4911ms 133.4922 Ops/s 133.4390 Ops/s $\color{#35bf28}+0.04\%$
test_ppo_speed 8.8910ms 7.7619ms 128.8342 Ops/s 127.5149 Ops/s $\color{#35bf28}+1.03\%$
test_reinforce_speed 7.2150ms 6.6672ms 149.9885 Ops/s 150.5329 Ops/s $\color{#d91a1a}-0.36\%$
test_iql_speed 33.7131ms 32.5051ms 30.7644 Ops/s 30.1419 Ops/s $\color{#35bf28}+2.07\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.5989ms 2.2919ms 436.3257 Ops/s 432.0936 Ops/s $\color{#35bf28}+0.98\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8107ms 0.5044ms 1.9824 KOps/s 1.9709 KOps/s $\color{#35bf28}+0.59\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 3.7350ms 0.4815ms 2.0769 KOps/s 2.0647 KOps/s $\color{#35bf28}+0.59\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.6445ms 2.2013ms 454.2728 Ops/s 442.3035 Ops/s $\color{#35bf28}+2.71\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9499ms 0.5211ms 1.9189 KOps/s 2.0084 KOps/s $\color{#d91a1a}-4.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7506ms 0.4679ms 2.1373 KOps/s 2.1091 KOps/s $\color{#35bf28}+1.34\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.5894ms 2.3556ms 424.5136 Ops/s 421.4313 Ops/s $\color{#35bf28}+0.73\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0378ms 0.6182ms 1.6175 KOps/s 1.6294 KOps/s $\color{#d91a1a}-0.73\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9042ms 0.5932ms 1.6859 KOps/s 1.7056 KOps/s $\color{#d91a1a}-1.16\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.5983ms 2.2183ms 450.7998 Ops/s 451.1647 Ops/s $\color{#d91a1a}-0.08\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 89.8052ms 0.6020ms 1.6612 KOps/s 2.0056 KOps/s $\textbf{\color{#d91a1a}-17.17\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5620ms 0.4738ms 2.1105 KOps/s 1.7437 KOps/s $\textbf{\color{#35bf28}+21.03\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.6658ms 2.2493ms 444.5849 Ops/s 417.5543 Ops/s $\textbf{\color{#35bf28}+6.47\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7828ms 0.5007ms 1.9972 KOps/s 1.9800 KOps/s $\color{#35bf28}+0.87\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.7042ms 0.4720ms 2.1186 KOps/s 2.0806 KOps/s $\color{#35bf28}+1.83\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.6737ms 2.4098ms 414.9754 Ops/s 421.5875 Ops/s $\color{#d91a1a}-1.57\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9371ms 0.6279ms 1.5925 KOps/s 1.6406 KOps/s $\color{#d91a1a}-2.93\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 3.6646ms 0.5933ms 1.6854 KOps/s 1.6847 KOps/s $\color{#35bf28}+0.04\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1068s 5.6814ms 176.0123 Ops/s 185.7074 Ops/s $\textbf{\color{#d91a1a}-5.22\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.5122ms 12.2527ms 81.6145 Ops/s 80.5358 Ops/s $\color{#35bf28}+1.34\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.6998ms 1.0345ms 966.6579 Ops/s 965.1913 Ops/s $\color{#35bf28}+0.15\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 88.5854ms 6.9627ms 143.6228 Ops/s 136.3820 Ops/s $\textbf{\color{#35bf28}+5.31\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.3167ms 12.0029ms 83.3134 Ops/s 83.2526 Ops/s $\color{#35bf28}+0.07\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.5021ms 1.0350ms 966.2183 Ops/s 826.2432 Ops/s $\textbf{\color{#35bf28}+16.94\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 96.3219ms 5.8246ms 171.6869 Ops/s 122.6787 Ops/s $\textbf{\color{#35bf28}+39.95\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1026s 14.4179ms 69.3581 Ops/s 79.3531 Ops/s $\textbf{\color{#d91a1a}-12.60\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.0121ms 1.6014ms 624.4423 Ops/s 743.2665 Ops/s $\textbf{\color{#d91a1a}-15.99\%}$

@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 23, 2024 •
edited
Loading

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1136s 0.1129s 8.8552 Ops/s 8.6037 Ops/s $\color{#35bf28}+2.92\%$
test_sync 95.9952ms 95.4818ms 10.4732 Ops/s 10.3800 Ops/s $\color{#35bf28}+0.90\%$
test_async 0.1811s 91.7055ms 10.9045 Ops/s 10.9133 Ops/s $\color{#d91a1a}-0.08\%$
test_single_pixels 0.2018s 0.1393s 7.1770 Ops/s 7.4421 Ops/s $\color{#d91a1a}-3.56\%$
test_sync_pixels 84.0371ms 82.1850ms 12.1677 Ops/s 11.9839 Ops/s $\color{#35bf28}+1.53\%$
test_async_pixels 0.1515s 64.5160ms 15.5000 Ops/s 14.7946 Ops/s $\color{#35bf28}+4.77\%$
test_simple 0.8144s 0.8078s 1.2380 Ops/s 1.1892 Ops/s $\color{#35bf28}+4.10\%$
test_transformed 1.0288s 1.0278s 0.9730 Ops/s 0.9421 Ops/s $\color{#35bf28}+3.28\%$
test_serial 2.4304s 2.3765s 0.4208 Ops/s 0.4095 Ops/s $\color{#35bf28}+2.76\%$
test_parallel 2.1081s 2.0657s 0.4841 Ops/s 0.4760 Ops/s $\color{#35bf28}+1.69\%$
test_step_mdp_speed[True-True-True-True-True] 99.0110μs 33.1273μs 30.1866 KOps/s 30.5644 KOps/s $\color{#d91a1a}-1.24\%$
test_step_mdp_speed[True-True-True-True-False] 36.2610μs 19.5023μs 51.2759 KOps/s 51.3594 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[True-True-True-False-True] 36.9300μs 18.7395μs 53.3632 KOps/s 54.3143 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[True-True-True-False-False] 28.3410μs 10.9189μs 91.5846 KOps/s 90.1278 KOps/s $\color{#35bf28}+1.62\%$
test_step_mdp_speed[True-True-False-True-True] 55.9410μs 34.4520μs 29.0259 KOps/s 29.8603 KOps/s $\color{#d91a1a}-2.79\%$
test_step_mdp_speed[True-True-False-True-False] 39.4200μs 21.1844μs 47.2046 KOps/s 47.7400 KOps/s $\color{#d91a1a}-1.12\%$
test_step_mdp_speed[True-True-False-False-True] 44.9910μs 20.1063μs 49.7356 KOps/s 49.6161 KOps/s $\color{#35bf28}+0.24\%$
test_step_mdp_speed[True-True-False-False-False] 31.9100μs 12.8353μs 77.9103 KOps/s 77.3652 KOps/s $\color{#35bf28}+0.70\%$
test_step_mdp_speed[True-False-True-True-True] 59.5000μs 36.7321μs 27.2241 KOps/s 27.8280 KOps/s $\color{#d91a1a}-2.17\%$
test_step_mdp_speed[True-False-True-True-False] 52.1010μs 22.9515μs 43.5701 KOps/s 42.8379 KOps/s $\color{#35bf28}+1.71\%$
test_step_mdp_speed[True-False-True-False-True] 48.5310μs 20.1900μs 49.5294 KOps/s 49.5199 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[True-False-True-False-False] 36.5810μs 12.6393μs 79.1182 KOps/s 78.2034 KOps/s $\color{#35bf28}+1.17\%$
test_step_mdp_speed[True-False-False-True-True] 61.3310μs 38.4782μs 25.9888 KOps/s 26.3117 KOps/s $\color{#d91a1a}-1.23\%$
test_step_mdp_speed[True-False-False-True-False] 43.3000μs 24.6506μs 40.5669 KOps/s 40.1461 KOps/s $\color{#35bf28}+1.05\%$
test_step_mdp_speed[True-False-False-False-True] 51.7000μs 21.8439μs 45.7793 KOps/s 45.8307 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[True-False-False-False-False] 31.4810μs 14.5415μs 68.7687 KOps/s 68.4740 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[False-True-True-True-True] 58.0100μs 35.9860μs 27.7886 KOps/s 27.5421 KOps/s $\color{#35bf28}+0.90\%$
test_step_mdp_speed[False-True-True-True-False] 39.8600μs 22.9383μs 43.5951 KOps/s 43.7199 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[False-True-True-False-True] 44.2910μs 23.8550μs 41.9199 KOps/s 42.4003 KOps/s $\color{#d91a1a}-1.13\%$
test_step_mdp_speed[False-True-True-False-False] 40.8100μs 14.8093μs 67.5251 KOps/s 66.7418 KOps/s $\color{#35bf28}+1.17\%$
test_step_mdp_speed[False-True-False-True-True] 59.5610μs 38.1998μs 26.1781 KOps/s 26.2271 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[False-True-False-True-False] 42.5310μs 25.1294μs 39.7941 KOps/s 39.9289 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[False-True-False-False-True] 50.9000μs 25.7389μs 38.8518 KOps/s 38.8592 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[False-True-False-False-False] 58.4710μs 16.5281μs 60.5029 KOps/s 60.4236 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[False-False-True-True-True] 57.5610μs 40.1969μs 24.8775 KOps/s 25.2173 KOps/s $\color{#d91a1a}-1.35\%$
test_step_mdp_speed[False-False-True-True-False] 43.9910μs 26.8170μs 37.2898 KOps/s 37.0645 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[False-False-True-False-True] 41.8100μs 25.9414μs 38.5485 KOps/s 39.8398 KOps/s $\color{#d91a1a}-3.24\%$
test_step_mdp_speed[False-False-True-False-False] 41.8010μs 16.6894μs 59.9183 KOps/s 60.6006 KOps/s $\color{#d91a1a}-1.13\%$
test_step_mdp_speed[False-False-False-True-True] 57.7200μs 41.5757μs 24.0525 KOps/s 24.0906 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[False-False-False-True-False] 50.2310μs 28.5593μs 35.0149 KOps/s 34.6542 KOps/s $\color{#35bf28}+1.04\%$
test_step_mdp_speed[False-False-False-False-True] 47.5210μs 27.3176μs 36.6065 KOps/s 37.0897 KOps/s $\color{#d91a1a}-1.30\%$
test_step_mdp_speed[False-False-False-False-False] 54.9000μs 18.3247μs 54.5712 KOps/s 54.3776 KOps/s $\color{#35bf28}+0.36\%$
test_values[generalized_advantage_estimate-True-True] 25.0119ms 24.6224ms 40.6134 Ops/s 37.4135 Ops/s $\textbf{\color{#35bf28}+8.55\%}$
test_values[vec_generalized_advantage_estimate-True-True] 85.4072ms 3.2702ms 305.7961 Ops/s 305.3665 Ops/s $\color{#35bf28}+0.14\%$
test_values[td0_return_estimate-False-False] 0.1073ms 61.4040μs 16.2856 KOps/s 16.0919 KOps/s $\color{#35bf28}+1.20\%$
test_values[td1_return_estimate-False-False] 57.7968ms 54.8851ms 18.2199 Ops/s 17.7067 Ops/s $\color{#35bf28}+2.90\%$
test_values[vec_td1_return_estimate-False-False] 2.1360ms 1.7606ms 567.9771 Ops/s 554.5612 Ops/s $\color{#35bf28}+2.42\%$
test_values[td_lambda_return_estimate-True-False] 84.8147ms 84.4354ms 11.8434 Ops/s 10.8417 Ops/s $\textbf{\color{#35bf28}+9.24\%}$
test_values[vec_td_lambda_return_estimate-True-False] 4.0220ms 1.7919ms 558.0739 Ops/s 554.0077 Ops/s $\color{#35bf28}+0.73\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.1608ms 23.4338ms 42.6733 Ops/s 42.3024 Ops/s $\color{#35bf28}+0.88\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8791ms 0.7037ms 1.4210 KOps/s 1.4067 KOps/s $\color{#35bf28}+1.01\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7119ms 0.6511ms 1.5359 KOps/s 1.5212 KOps/s $\color{#35bf28}+0.97\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5001ms 1.4514ms 688.9944 Ops/s 685.0492 Ops/s $\color{#35bf28}+0.58\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9514ms 0.6697ms 1.4932 KOps/s 1.4758 KOps/s $\color{#35bf28}+1.17\%$
test_dqn_speed 8.3058ms 1.4569ms 686.3870 Ops/s 600.4059 Ops/s $\textbf{\color{#35bf28}+14.32\%}$
test_ddpg_speed 3.3764ms 2.8247ms 354.0218 Ops/s 342.3328 Ops/s $\color{#35bf28}+3.41\%$
test_sac_speed 8.6037ms 8.0586ms 124.0911 Ops/s 121.2174 Ops/s $\color{#35bf28}+2.37\%$
test_redq_speed 11.2577ms 10.1412ms 98.6073 Ops/s 96.2278 Ops/s $\color{#35bf28}+2.47\%$
test_redq_deprec_speed 11.0985ms 10.7420ms 93.0926 Ops/s 85.1735 Ops/s $\textbf{\color{#35bf28}+9.30\%}$
test_td3_speed 8.2908ms 8.0423ms 124.3426 Ops/s 119.7870 Ops/s $\color{#35bf28}+3.80\%$
test_cql_speed 25.2811ms 24.8380ms 40.2609 Ops/s 38.4452 Ops/s $\color{#35bf28}+4.72\%$
test_a2c_speed 5.6974ms 5.4307ms 184.1374 Ops/s 169.8724 Ops/s $\textbf{\color{#35bf28}+8.40\%}$
test_ppo_speed 6.9714ms 5.8438ms 171.1214 Ops/s 164.1087 Ops/s $\color{#35bf28}+4.27\%$
test_reinforce_speed 4.6639ms 4.4180ms 226.3479 Ops/s 211.8949 Ops/s $\textbf{\color{#35bf28}+6.82\%}$
test_iql_speed 19.5821ms 18.9491ms 52.7729 Ops/s 49.9150 Ops/s $\textbf{\color{#35bf28}+5.73\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0124ms 2.8595ms 349.7142 Ops/s 346.0465 Ops/s $\color{#35bf28}+1.06\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1558ms 0.5440ms 1.8381 KOps/s 1.7807 KOps/s $\color{#35bf28}+3.22\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7108ms 0.5232ms 1.9112 KOps/s 1.8591 KOps/s $\color{#35bf28}+2.80\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.0767ms 2.8858ms 346.5236 Ops/s 343.8381 Ops/s $\color{#35bf28}+0.78\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2250ms 0.5395ms 1.8535 KOps/s 1.8038 KOps/s $\color{#35bf28}+2.76\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6950ms 0.5166ms 1.9357 KOps/s 1.8732 KOps/s $\color{#35bf28}+3.33\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1203ms 2.9841ms 335.1103 Ops/s 330.1972 Ops/s $\color{#35bf28}+1.49\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2274ms 0.6678ms 1.4974 KOps/s 1.4379 KOps/s $\color{#35bf28}+4.14\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8651ms 0.6460ms 1.5481 KOps/s 1.4907 KOps/s $\color{#35bf28}+3.85\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0206ms 2.8831ms 346.8457 Ops/s 345.0945 Ops/s $\color{#35bf28}+0.51\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0795ms 0.5489ms 1.8217 KOps/s 1.7765 KOps/s $\color{#35bf28}+2.54\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6978ms 0.5248ms 1.9056 KOps/s 1.5993 KOps/s $\textbf{\color{#35bf28}+19.15\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1408ms 2.9019ms 344.6003 Ops/s 341.2636 Ops/s $\color{#35bf28}+0.98\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7169ms 0.5411ms 1.8479 KOps/s 1.7931 KOps/s $\color{#35bf28}+3.06\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.6238ms 0.5243ms 1.9072 KOps/s 1.8695 KOps/s $\color{#35bf28}+2.02\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1369ms 3.0043ms 332.8580 Ops/s 327.9264 Ops/s $\color{#35bf28}+1.50\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8370ms 0.6763ms 1.4786 KOps/s 1.4381 KOps/s $\color{#35bf28}+2.82\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 4.8472ms 0.6537ms 1.5298 KOps/s 1.5025 KOps/s $\color{#35bf28}+1.82\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1048s 8.6921ms 115.0465 Ops/s 145.6965 Ops/s $\textbf{\color{#d91a1a}-21.04\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.3420ms 14.3229ms 69.8183 Ops/s 64.4361 Ops/s $\textbf{\color{#35bf28}+8.35\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.1526ms 1.0874ms 919.6168 Ops/s 919.6540 Ops/s $-0.00\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1003s 6.6644ms 150.0507 Ops/s 115.6733 Ops/s $\textbf{\color{#35bf28}+29.72\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.7519ms 14.3734ms 69.5728 Ops/s 66.2152 Ops/s $\textbf{\color{#35bf28}+5.07\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.1111ms 1.0886ms 918.5815 Ops/s 914.3370 Ops/s $\color{#35bf28}+0.46\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1030s 8.9839ms 111.3099 Ops/s 140.7009 Ops/s $\textbf{\color{#d91a1a}-20.89\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.0909ms 14.6437ms 68.2887 Ops/s 64.4376 Ops/s $\textbf{\color{#35bf28}+5.98\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.4568ms 1.4061ms 711.2011 Ops/s 685.4327 Ops/s $\color{#35bf28}+3.76\%$

@vmoens vmoens added bug Something isn't working enhancement New feature or request labels Feb 23, 2024
@vmoens vmoens merged commit 492091a into main Feb 23, 2024
63 of 67 checks passed
@vmoens vmoens deleted the refactor-split-traj branch February 23, 2024 02:13
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. enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

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