Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[BugFix] Fix device of container generated values in transforms #1827

Merged
merged 1 commit into from
Jan 22, 2024
Merged

[BugFix] Fix device of container generated values in transforms #1827

merged 1 commit into from
Jan 22, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Jan 22, 2024

Fixes a bug reported in #1198 (comment)

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Jan 22, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1827

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

⏳ 1 Pending, 5 Unrelated Failures

As of commit f43262a with merge base 3f04131 (image):

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

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 Jan 22, 2024
@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1465s 66.7612ms 14.9788 Ops/s 16.9169 Ops/s $\textbf{\color{#d91a1a}-11.46\%}$
test_sync 40.0086ms 34.9027ms 28.6511 Ops/s 28.8812 Ops/s $\color{#d91a1a}-0.80\%$
test_async 62.0302ms 31.6193ms 31.6263 Ops/s 30.6451 Ops/s $\color{#35bf28}+3.20\%$
test_simple 0.4971s 0.4315s 2.3177 Ops/s 2.3610 Ops/s $\color{#d91a1a}-1.84\%$
test_transformed 0.6385s 0.5863s 1.7058 Ops/s 1.7359 Ops/s $\color{#d91a1a}-1.74\%$
test_serial 1.3873s 1.3350s 0.7491 Ops/s 0.7678 Ops/s $\color{#d91a1a}-2.44\%$
test_parallel 1.2125s 1.1720s 0.8532 Ops/s 0.8589 Ops/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-True-True-True-True] 0.1518ms 21.1185μs 47.3519 KOps/s 47.7946 KOps/s $\color{#d91a1a}-0.93\%$
test_step_mdp_speed[True-True-True-True-False] 47.8890μs 13.1638μs 75.9661 KOps/s 77.1474 KOps/s $\color{#d91a1a}-1.53\%$
test_step_mdp_speed[True-True-True-False-True] 45.0640μs 12.3670μs 80.8602 KOps/s 81.9696 KOps/s $\color{#d91a1a}-1.35\%$
test_step_mdp_speed[True-True-True-False-False] 27.9120μs 7.5904μs 131.7448 KOps/s 132.5497 KOps/s $\color{#d91a1a}-0.61\%$
test_step_mdp_speed[True-True-False-True-True] 52.7890μs 22.4791μs 44.4858 KOps/s 44.8538 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[True-True-False-True-False] 43.0000μs 14.3165μs 69.8494 KOps/s 70.3493 KOps/s $\color{#d91a1a}-0.71\%$
test_step_mdp_speed[True-True-False-False-True] 46.8570μs 13.6658μs 73.1754 KOps/s 73.1597 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[True-True-False-False-False] 0.1277ms 8.9499μs 111.7325 KOps/s 112.5002 KOps/s $\color{#d91a1a}-0.68\%$
test_step_mdp_speed[True-False-True-True-True] 52.3980μs 24.1341μs 41.4352 KOps/s 42.1729 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[True-False-True-True-False] 79.8580μs 15.6368μs 63.9519 KOps/s 64.3740 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-False-True-False-True] 39.7450μs 13.6237μs 73.4017 KOps/s 73.6479 KOps/s $\color{#d91a1a}-0.33\%$
test_step_mdp_speed[True-False-True-False-False] 55.7440μs 8.8602μs 112.8640 KOps/s 113.3773 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[True-False-False-True-True] 56.8160μs 25.1618μs 39.7429 KOps/s 39.9938 KOps/s $\color{#d91a1a}-0.63\%$
test_step_mdp_speed[True-False-False-True-False] 90.2380μs 16.7065μs 59.8568 KOps/s 59.9380 KOps/s $\color{#d91a1a}-0.14\%$
test_step_mdp_speed[True-False-False-False-True] 41.6970μs 14.5552μs 68.7038 KOps/s 67.8073 KOps/s $\color{#35bf28}+1.32\%$
test_step_mdp_speed[True-False-False-False-False] 34.8550μs 10.0671μs 99.3337 KOps/s 100.7810 KOps/s $\color{#d91a1a}-1.44\%$
test_step_mdp_speed[False-True-True-True-True] 0.1110ms 23.9020μs 41.8375 KOps/s 42.1121 KOps/s $\color{#d91a1a}-0.65\%$
test_step_mdp_speed[False-True-True-True-False] 0.1868ms 16.3604μs 61.1233 KOps/s 64.4508 KOps/s $\textbf{\color{#d91a1a}-5.16\%}$
test_step_mdp_speed[False-True-True-False-True] 39.2230μs 15.8202μs 63.2104 KOps/s 62.5926 KOps/s $\color{#35bf28}+0.99\%$
test_step_mdp_speed[False-True-True-False-False] 32.4000μs 10.0666μs 99.3383 KOps/s 101.1671 KOps/s $\color{#d91a1a}-1.81\%$
test_step_mdp_speed[False-True-False-True-True] 70.4010μs 25.2733μs 39.5675 KOps/s 40.0511 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[False-True-False-True-False] 54.7930μs 16.9816μs 58.8872 KOps/s 59.4379 KOps/s $\color{#d91a1a}-0.93\%$
test_step_mdp_speed[False-True-False-False-True] 42.3990μs 17.1435μs 58.3310 KOps/s 58.5166 KOps/s $\color{#d91a1a}-0.32\%$
test_step_mdp_speed[False-True-False-False-False] 49.3720μs 11.3290μs 88.2692 KOps/s 89.1106 KOps/s $\color{#d91a1a}-0.94\%$
test_step_mdp_speed[False-False-True-True-True] 65.3220μs 26.5956μs 37.6002 KOps/s 37.9121 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[False-False-True-True-False] 43.6910μs 18.4217μs 54.2839 KOps/s 55.3234 KOps/s $\color{#d91a1a}-1.88\%$
test_step_mdp_speed[False-False-True-False-True] 58.3990μs 17.0755μs 58.5634 KOps/s 59.3222 KOps/s $\color{#d91a1a}-1.28\%$
test_step_mdp_speed[False-False-True-False-False] 34.7850μs 11.3932μs 87.7713 KOps/s 89.7472 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[False-False-False-True-True] 0.2072ms 27.5322μs 36.3211 KOps/s 36.4790 KOps/s $\color{#d91a1a}-0.43\%$
test_step_mdp_speed[False-False-False-True-False] 68.3370μs 19.2865μs 51.8496 KOps/s 52.4889 KOps/s $\color{#d91a1a}-1.22\%$
test_step_mdp_speed[False-False-False-False-True] 60.6130μs 18.0466μs 55.4119 KOps/s 55.4617 KOps/s $\color{#d91a1a}-0.09\%$
test_step_mdp_speed[False-False-False-False-False] 50.2840μs 12.3734μs 80.8184 KOps/s 81.6052 KOps/s $\color{#d91a1a}-0.96\%$
test_values[generalized_advantage_estimate-True-True] 13.1034ms 12.0458ms 83.0163 Ops/s 82.8469 Ops/s $\color{#35bf28}+0.20\%$
test_values[vec_generalized_advantage_estimate-True-True] 35.6418ms 27.9292ms 35.8048 Ops/s 36.1371 Ops/s $\color{#d91a1a}-0.92\%$
test_values[td0_return_estimate-False-False] 0.2810ms 0.1955ms 5.1150 KOps/s 5.4485 KOps/s $\textbf{\color{#d91a1a}-6.12\%}$
test_values[td1_return_estimate-False-False] 26.9549ms 25.2700ms 39.5727 Ops/s 38.8541 Ops/s $\color{#35bf28}+1.85\%$
test_values[vec_td1_return_estimate-False-False] 35.5925ms 27.7949ms 35.9778 Ops/s 35.5345 Ops/s $\color{#35bf28}+1.25\%$
test_values[td_lambda_return_estimate-True-False] 45.4553ms 35.2068ms 28.4036 Ops/s 28.0650 Ops/s $\color{#35bf28}+1.21\%$
test_values[vec_td_lambda_return_estimate-True-False] 47.3349ms 28.3614ms 35.2592 Ops/s 35.8171 Ops/s $\color{#d91a1a}-1.56\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.0809ms 7.9669ms 125.5199 Ops/s 124.2272 Ops/s $\color{#35bf28}+1.04\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3436ms 1.8086ms 552.9123 Ops/s 521.2652 Ops/s $\textbf{\color{#35bf28}+6.07\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 9.0219ms 0.4267ms 2.3435 KOps/s 2.3650 KOps/s $\color{#d91a1a}-0.91\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 42.4400ms 36.8854ms 27.1110 Ops/s 24.3662 Ops/s $\textbf{\color{#35bf28}+11.26\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.6376ms 2.6097ms 383.1831 Ops/s 373.8495 Ops/s $\color{#35bf28}+2.50\%$
test_dqn_speed 84.9483ms 8.1122ms 123.2711 Ops/s 129.2495 Ops/s $\color{#d91a1a}-4.63\%$
test_ddpg_speed 18.6413ms 14.2471ms 70.1898 Ops/s 71.3359 Ops/s $\color{#d91a1a}-1.61\%$
test_sac_speed 30.9181ms 29.0043ms 34.4777 Ops/s 35.3058 Ops/s $\color{#d91a1a}-2.35\%$
test_redq_speed 50.2179ms 45.2304ms 22.1090 Ops/s 22.2651 Ops/s $\color{#d91a1a}-0.70\%$
test_redq_deprec_speed 29.6071ms 25.4298ms 39.3239 Ops/s 39.9924 Ops/s $\color{#d91a1a}-1.67\%$
test_td3_speed 30.7230ms 20.2944ms 49.2747 Ops/s 50.7053 Ops/s $\color{#d91a1a}-2.82\%$
test_cql_speed 91.9003ms 86.8875ms 11.5091 Ops/s 11.7907 Ops/s $\color{#d91a1a}-2.39\%$
test_a2c_speed 35.2202ms 26.4720ms 37.7758 Ops/s 37.9902 Ops/s $\color{#d91a1a}-0.56\%$
test_ppo_speed 38.7961ms 26.8937ms 37.1834 Ops/s 37.4246 Ops/s $\color{#d91a1a}-0.64\%$
test_reinforce_speed 34.8496ms 26.1392ms 38.2567 Ops/s 39.4830 Ops/s $\color{#d91a1a}-3.11\%$
test_iql_speed 71.4654ms 64.0566ms 15.6112 Ops/s 16.1789 Ops/s $\color{#d91a1a}-3.51\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.0963ms 1.3917ms 718.5308 Ops/s 727.9441 Ops/s $\color{#d91a1a}-1.29\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 8.7083ms 0.5170ms 1.9344 KOps/s 1.9420 KOps/s $\color{#d91a1a}-0.39\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 8.8688ms 0.4892ms 2.0443 KOps/s 2.0440 KOps/s $\color{#35bf28}+0.01\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 1.7419ms 1.3428ms 744.7330 Ops/s 738.9109 Ops/s $\color{#35bf28}+0.79\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 8.7295ms 0.5116ms 1.9547 KOps/s 1.9783 KOps/s $\color{#d91a1a}-1.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7159ms 0.4819ms 2.0751 KOps/s 2.0635 KOps/s $\color{#35bf28}+0.56\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.5868ms 1.6297ms 613.5937 Ops/s 642.9530 Ops/s $\color{#d91a1a}-4.57\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 9.1159ms 0.6547ms 1.5275 KOps/s 1.5378 KOps/s $\color{#d91a1a}-0.68\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 9.0250ms 0.6235ms 1.6038 KOps/s 1.6060 KOps/s $\color{#d91a1a}-0.14\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.1390ms 1.3803ms 724.4759 Ops/s 727.2593 Ops/s $\color{#d91a1a}-0.38\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6242ms 0.5107ms 1.9580 KOps/s 1.9672 KOps/s $\color{#d91a1a}-0.47\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 8.8877ms 0.4967ms 2.0134 KOps/s 2.0272 KOps/s $\color{#d91a1a}-0.68\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.1438ms 1.4252ms 701.6754 Ops/s 727.2791 Ops/s $\color{#d91a1a}-3.52\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6262ms 0.5073ms 1.9712 KOps/s 1.9746 KOps/s $\color{#d91a1a}-0.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 9.4366ms 0.4929ms 2.0287 KOps/s 2.0854 KOps/s $\color{#d91a1a}-2.72\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.3911ms 1.5535ms 643.7078 Ops/s 642.5781 Ops/s $\color{#35bf28}+0.18\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.2131ms 0.6472ms 1.5450 KOps/s 1.5556 KOps/s $\color{#d91a1a}-0.68\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 12.6639ms 0.6701ms 1.4923 KOps/s 1.5914 KOps/s $\textbf{\color{#d91a1a}-6.23\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1191s 12.3891ms 80.7158 Ops/s 81.8031 Ops/s $\color{#d91a1a}-1.33\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 24.9527ms 13.7810ms 72.5639 Ops/s 73.1294 Ops/s $\color{#d91a1a}-0.77\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 5.4613ms 3.2448ms 308.1862 Ops/s 308.6987 Ops/s $\color{#d91a1a}-0.17\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1048s 10.2166ms 97.8802 Ops/s 98.4712 Ops/s $\color{#d91a1a}-0.60\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.3394ms 13.7012ms 72.9862 Ops/s 64.3838 Ops/s $\textbf{\color{#35bf28}+13.36\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 11.2725ms 3.4347ms 291.1427 Ops/s 292.0868 Ops/s $\color{#d91a1a}-0.32\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1043s 12.2990ms 81.3071 Ops/s 96.5094 Ops/s $\textbf{\color{#d91a1a}-15.75\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.5799ms 13.8892ms 71.9985 Ops/s 70.7898 Ops/s $\color{#35bf28}+1.71\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.5504ms 3.4995ms 285.7555 Ops/s 283.6356 Ops/s $\color{#35bf28}+0.75\%$

@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1173s 0.1139s 8.7778 Ops/s 8.7645 Ops/s $\color{#35bf28}+0.15\%$
test_sync 0.1732s 0.1028s 9.7282 Ops/s 9.7655 Ops/s $\color{#d91a1a}-0.38\%$
test_async 0.1811s 91.4857ms 10.9307 Ops/s 10.8945 Ops/s $\color{#35bf28}+0.33\%$
test_single_pixels 0.1264s 0.1258s 7.9508 Ops/s 7.2662 Ops/s $\textbf{\color{#35bf28}+9.42\%}$
test_sync_pixels 77.8526ms 76.5668ms 13.0605 Ops/s 13.2071 Ops/s $\color{#d91a1a}-1.11\%$
test_async_pixels 0.1319s 69.9236ms 14.3013 Ops/s 14.2821 Ops/s $\color{#35bf28}+0.13\%$
test_simple 0.9129s 0.8369s 1.1950 Ops/s 1.2290 Ops/s $\color{#d91a1a}-2.77\%$
test_transformed 1.0554s 1.0518s 0.9508 Ops/s 0.9507 Ops/s $+0.01\%$
test_serial 2.4052s 2.3062s 0.4336 Ops/s 0.4365 Ops/s $\color{#d91a1a}-0.67\%$
test_parallel 2.1440s 1.8966s 0.5272 Ops/s 0.5330 Ops/s $\color{#d91a1a}-1.07\%$
test_step_mdp_speed[True-True-True-True-True] 81.8220μs 31.8444μs 31.4027 KOps/s 30.7333 KOps/s $\color{#35bf28}+2.18\%$
test_step_mdp_speed[True-True-True-True-False] 43.5800μs 19.1965μs 52.0928 KOps/s 52.0140 KOps/s $\color{#35bf28}+0.15\%$
test_step_mdp_speed[True-True-True-False-True] 44.3010μs 17.8904μs 55.8960 KOps/s 54.4315 KOps/s $\color{#35bf28}+2.69\%$
test_step_mdp_speed[True-True-True-False-False] 32.0310μs 10.8506μs 92.1604 KOps/s 90.6939 KOps/s $\color{#35bf28}+1.62\%$
test_step_mdp_speed[True-True-False-True-True] 0.1069ms 33.3977μs 29.9422 KOps/s 29.5260 KOps/s $\color{#35bf28}+1.41\%$
test_step_mdp_speed[True-True-False-True-False] 51.8410μs 20.8810μs 47.8904 KOps/s 47.2747 KOps/s $\color{#35bf28}+1.30\%$
test_step_mdp_speed[True-True-False-False-True] 45.2810μs 19.7311μs 50.6815 KOps/s 49.5284 KOps/s $\color{#35bf28}+2.33\%$
test_step_mdp_speed[True-True-False-False-False] 34.5200μs 12.7725μs 78.2931 KOps/s 77.1619 KOps/s $\color{#35bf28}+1.47\%$
test_step_mdp_speed[True-False-True-True-True] 66.9610μs 35.5966μs 28.0926 KOps/s 28.0323 KOps/s $\color{#35bf28}+0.21\%$
test_step_mdp_speed[True-False-True-True-False] 48.4110μs 22.9286μs 43.6137 KOps/s 43.0916 KOps/s $\color{#35bf28}+1.21\%$
test_step_mdp_speed[True-False-True-False-True] 43.3400μs 19.6710μs 50.8363 KOps/s 50.5161 KOps/s $\color{#35bf28}+0.63\%$
test_step_mdp_speed[True-False-True-False-False] 34.7110μs 12.6313μs 79.1685 KOps/s 77.2170 KOps/s $\color{#35bf28}+2.53\%$
test_step_mdp_speed[True-False-False-True-True] 76.3920μs 37.6303μs 26.5743 KOps/s 26.4251 KOps/s $\color{#35bf28}+0.56\%$
test_step_mdp_speed[True-False-False-True-False] 49.8500μs 24.7017μs 40.4830 KOps/s 40.2724 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-False-False-False-True] 45.7000μs 21.4401μs 46.6415 KOps/s 46.0267 KOps/s $\color{#35bf28}+1.34\%$
test_step_mdp_speed[True-False-False-False-False] 90.5720μs 14.4186μs 69.3549 KOps/s 68.1133 KOps/s $\color{#35bf28}+1.82\%$
test_step_mdp_speed[False-True-True-True-True] 64.0820μs 36.3136μs 27.5379 KOps/s 28.2479 KOps/s $\color{#d91a1a}-2.51\%$
test_step_mdp_speed[False-True-True-True-False] 47.4610μs 22.7333μs 43.9883 KOps/s 43.4426 KOps/s $\color{#35bf28}+1.26\%$
test_step_mdp_speed[False-True-True-False-True] 50.8610μs 23.5872μs 42.3958 KOps/s 42.0978 KOps/s $\color{#35bf28}+0.71\%$
test_step_mdp_speed[False-True-True-False-False] 35.6800μs 14.6976μs 68.0383 KOps/s 68.2623 KOps/s $\color{#d91a1a}-0.33\%$
test_step_mdp_speed[False-True-False-True-True] 74.3320μs 37.2409μs 26.8522 KOps/s 26.5326 KOps/s $\color{#35bf28}+1.20\%$
test_step_mdp_speed[False-True-False-True-False] 98.7010μs 24.5778μs 40.6871 KOps/s 40.3186 KOps/s $\color{#35bf28}+0.91\%$
test_step_mdp_speed[False-True-False-False-True] 51.6110μs 25.5179μs 39.1882 KOps/s 39.2316 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[False-True-False-False-False] 44.2210μs 16.3025μs 61.3403 KOps/s 61.1023 KOps/s $\color{#35bf28}+0.39\%$
test_step_mdp_speed[False-False-True-True-True] 70.0920μs 39.1517μs 25.5417 KOps/s 25.2813 KOps/s $\color{#35bf28}+1.03\%$
test_step_mdp_speed[False-False-True-True-False] 53.4310μs 26.4781μs 37.7670 KOps/s 37.3429 KOps/s $\color{#35bf28}+1.14\%$
test_step_mdp_speed[False-False-True-False-True] 0.1262ms 25.3168μs 39.4995 KOps/s 39.5078 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[False-False-True-False-False] 41.4710μs 16.0055μs 62.4786 KOps/s 60.9515 KOps/s $\color{#35bf28}+2.51\%$
test_step_mdp_speed[False-False-False-True-True] 77.5810μs 40.2761μs 24.8286 KOps/s 24.7443 KOps/s $\color{#35bf28}+0.34\%$
test_step_mdp_speed[False-False-False-True-False] 52.5010μs 27.9642μs 35.7600 KOps/s 35.3616 KOps/s $\color{#35bf28}+1.13\%$
test_step_mdp_speed[False-False-False-False-True] 52.9710μs 26.8094μs 37.3004 KOps/s 37.2235 KOps/s $\color{#35bf28}+0.21\%$
test_step_mdp_speed[False-False-False-False-False] 50.5510μs 17.9552μs 55.6941 KOps/s 55.1711 KOps/s $\color{#35bf28}+0.95\%$
test_values[generalized_advantage_estimate-True-True] 25.4789ms 25.0731ms 39.8835 Ops/s 40.4883 Ops/s $\color{#d91a1a}-1.49\%$
test_values[vec_generalized_advantage_estimate-True-True] 87.6857ms 3.3056ms 302.5145 Ops/s 314.6844 Ops/s $\color{#d91a1a}-3.87\%$
test_values[td0_return_estimate-False-False] 95.1420μs 59.9830μs 16.6714 KOps/s 16.4392 KOps/s $\color{#35bf28}+1.41\%$
test_values[td1_return_estimate-False-False] 54.3937ms 53.7495ms 18.6048 Ops/s 18.5216 Ops/s $\color{#35bf28}+0.45\%$
test_values[vec_td1_return_estimate-False-False] 2.1029ms 1.7680ms 565.6178 Ops/s 557.5730 Ops/s $\color{#35bf28}+1.44\%$
test_values[td_lambda_return_estimate-True-False] 87.1927ms 86.3254ms 11.5841 Ops/s 11.5495 Ops/s $\color{#35bf28}+0.30\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.1098ms 1.7672ms 565.8739 Ops/s 564.7779 Ops/s $\color{#35bf28}+0.19\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.3070ms 23.9749ms 41.7103 Ops/s 41.9426 Ops/s $\color{#d91a1a}-0.55\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8775ms 0.7018ms 1.4249 KOps/s 1.4603 KOps/s $\color{#d91a1a}-2.42\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7246ms 0.6678ms 1.4974 KOps/s 1.5612 KOps/s $\color{#d91a1a}-4.08\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5243ms 1.4663ms 681.9997 Ops/s 679.6246 Ops/s $\color{#35bf28}+0.35\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9248ms 0.6625ms 1.5095 KOps/s 1.4544 KOps/s $\color{#35bf28}+3.79\%$
test_dqn_speed 7.5775ms 7.2158ms 138.5843 Ops/s 136.1646 Ops/s $\color{#35bf28}+1.78\%$
test_ddpg_speed 0.1003s 15.5920ms 64.1356 Ops/s 69.8987 Ops/s $\textbf{\color{#d91a1a}-8.24\%}$
test_sac_speed 30.1574ms 29.1235ms 34.3366 Ops/s 34.1049 Ops/s $\color{#35bf28}+0.68\%$
test_redq_speed 49.1092ms 47.0719ms 21.2441 Ops/s 20.9255 Ops/s $\color{#35bf28}+1.52\%$
test_redq_deprec_speed 25.4638ms 24.4046ms 40.9760 Ops/s 40.9533 Ops/s $\color{#35bf28}+0.06\%$
test_td3_speed 29.5722ms 19.8871ms 50.2838 Ops/s 49.9592 Ops/s $\color{#35bf28}+0.65\%$
test_cql_speed 84.1896ms 83.4555ms 11.9824 Ops/s 11.9718 Ops/s $\color{#35bf28}+0.09\%$
test_a2c_speed 27.4075ms 26.5785ms 37.6244 Ops/s 37.3290 Ops/s $\color{#35bf28}+0.79\%$
test_ppo_speed 27.9368ms 26.7659ms 37.3609 Ops/s 36.9372 Ops/s $\color{#35bf28}+1.15\%$
test_reinforce_speed 26.5964ms 25.6346ms 39.0097 Ops/s 38.6642 Ops/s $\color{#35bf28}+0.89\%$
test_iql_speed 59.5531ms 57.8479ms 17.2867 Ops/s 17.2887 Ops/s $\color{#d91a1a}-0.01\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.5862ms 1.8141ms 551.2318 Ops/s 542.5902 Ops/s $\color{#35bf28}+1.59\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9610ms 0.8432ms 1.1860 KOps/s 1.1762 KOps/s $\color{#35bf28}+0.83\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9539ms 0.8208ms 1.2183 KOps/s 1.2136 KOps/s $\color{#35bf28}+0.38\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.6076ms 1.7807ms 561.5663 Ops/s 547.0148 Ops/s $\color{#35bf28}+2.66\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.3467ms 0.8328ms 1.2008 KOps/s 1.1966 KOps/s $\color{#35bf28}+0.35\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.9657ms 0.8094ms 1.2354 KOps/s 1.2301 KOps/s $\color{#35bf28}+0.44\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 0.1224s 2.3091ms 433.0707 Ops/s 477.8007 Ops/s $\textbf{\color{#d91a1a}-9.36\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1140ms 0.9589ms 1.0428 KOps/s 1.0335 KOps/s $\color{#35bf28}+0.90\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0806ms 0.9403ms 1.0635 KOps/s 1.0555 KOps/s $\color{#35bf28}+0.76\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 0.1271s 2.0750ms 481.9359 Ops/s 539.7021 Ops/s $\textbf{\color{#d91a1a}-10.70\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9752ms 0.8465ms 1.1814 KOps/s 1.1763 KOps/s $\color{#35bf28}+0.43\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9585ms 0.8228ms 1.2154 KOps/s 1.2087 KOps/s $\color{#35bf28}+0.56\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 1.8887ms 1.7779ms 562.4613 Ops/s 548.7592 Ops/s $\color{#35bf28}+2.50\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9933ms 0.8319ms 1.2020 KOps/s 1.1915 KOps/s $\color{#35bf28}+0.88\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.9494ms 0.8109ms 1.2332 KOps/s 1.2292 KOps/s $\color{#35bf28}+0.33\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.0469ms 2.0473ms 488.4450 Ops/s 418.8781 Ops/s $\textbf{\color{#35bf28}+16.61\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.1180s 1.1049ms 905.0590 Ops/s 1.0374 KOps/s $\textbf{\color{#d91a1a}-12.76\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0640ms 0.9400ms 1.0638 KOps/s 1.0607 KOps/s $\color{#35bf28}+0.30\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1209s 10.0660ms 99.3440 Ops/s 93.1094 Ops/s $\textbf{\color{#35bf28}+6.70\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.1272ms 13.7251ms 72.8590 Ops/s 71.2675 Ops/s $\color{#35bf28}+2.23\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.0712ms 3.3529ms 298.2517 Ops/s 295.5527 Ops/s $\color{#35bf28}+0.91\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1191s 9.9160ms 100.8474 Ops/s 100.7205 Ops/s $\color{#35bf28}+0.13\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.1672ms 13.6192ms 73.4259 Ops/s 72.3743 Ops/s $\color{#35bf28}+1.45\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.3506ms 3.3472ms 298.7601 Ops/s 295.2374 Ops/s $\color{#35bf28}+1.19\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1161s 10.0284ms 99.7166 Ops/s 96.7100 Ops/s $\color{#35bf28}+3.11\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1248s 16.0962ms 62.1264 Ops/s 61.2612 Ops/s $\color{#35bf28}+1.41\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.7607ms 3.5472ms 281.9102 Ops/s 279.7331 Ops/s $\color{#35bf28}+0.78\%$

@vmoens vmoens added the bug Something isn't working label Jan 22, 2024
@vmoens vmoens merged commit 55ec016 into main Jan 22, 2024
59 of 64 checks passed
@vmoens vmoens deleted the fix-stepcount-device branch January 22, 2024 17:24
@vmoens vmoens mentioned this pull request Jan 22, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Milestone
No milestone
Development

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