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] Fix offline CatFrames for pixels #1964

Merged
merged 1 commit into from
Feb 25, 2024
Merged

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 25, 2024

No description provided.

Copy link

pytorch-bot bot commented Feb 25, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1964

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

❌ 1 New Failure, 1 Unrelated Failure

As of commit 50e469a with merge base 931f70a (image):

NEW FAILURE - The following job has 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 25, 2024
@vmoens vmoens added bug Something isn't working Suitable for minor Suitable to be integrated in minor release (no new feature) labels Feb 25, 2024
Copy link

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}4$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 63.0126ms 62.4163ms 16.0215 Ops/s 16.2766 Ops/s $\color{#d91a1a}-1.57\%$
test_sync 39.4872ms 33.8251ms 29.5638 Ops/s 29.9565 Ops/s $\color{#d91a1a}-1.31\%$
test_async 59.0792ms 30.7192ms 32.5529 Ops/s 30.7054 Ops/s $\textbf{\color{#35bf28}+6.02\%}$
test_simple 0.4929s 0.4409s 2.2680 Ops/s 2.2991 Ops/s $\color{#d91a1a}-1.35\%$
test_transformed 0.6424s 0.5984s 1.6711 Ops/s 1.7008 Ops/s $\color{#d91a1a}-1.74\%$
test_serial 1.4978s 1.4762s 0.6774 Ops/s 0.6848 Ops/s $\color{#d91a1a}-1.07\%$
test_parallel 1.4482s 1.3990s 0.7148 Ops/s 0.7159 Ops/s $\color{#d91a1a}-0.15\%$
test_step_mdp_speed[True-True-True-True-True] 0.1840ms 21.5449μs 46.4148 KOps/s 47.3886 KOps/s $\color{#d91a1a}-2.05\%$
test_step_mdp_speed[True-True-True-True-False] 38.0610μs 13.1563μs 76.0093 KOps/s 77.1419 KOps/s $\color{#d91a1a}-1.47\%$
test_step_mdp_speed[True-True-True-False-True] 52.7590μs 12.7259μs 78.5799 KOps/s 80.7494 KOps/s $\color{#d91a1a}-2.69\%$
test_step_mdp_speed[True-True-True-False-False] 32.4210μs 7.6314μs 131.0382 KOps/s 131.4185 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[True-True-False-True-True] 53.9610μs 22.9567μs 43.5603 KOps/s 44.4088 KOps/s $\color{#d91a1a}-1.91\%$
test_step_mdp_speed[True-True-False-True-False] 47.1080μs 14.3957μs 69.4651 KOps/s 70.0236 KOps/s $\color{#d91a1a}-0.80\%$
test_step_mdp_speed[True-True-False-False-True] 41.9080μs 13.8954μs 71.9661 KOps/s 74.5222 KOps/s $\color{#d91a1a}-3.43\%$
test_step_mdp_speed[True-True-False-False-False] 37.9710μs 8.8617μs 112.8447 KOps/s 113.2181 KOps/s $\color{#d91a1a}-0.33\%$
test_step_mdp_speed[True-False-True-True-True] 69.7100μs 24.1860μs 41.3462 KOps/s 42.1261 KOps/s $\color{#d91a1a}-1.85\%$
test_step_mdp_speed[True-False-True-True-False] 41.0770μs 15.7912μs 63.3265 KOps/s 64.2157 KOps/s $\color{#d91a1a}-1.38\%$
test_step_mdp_speed[True-False-True-False-True] 53.3600μs 13.9577μs 71.6452 KOps/s 73.5390 KOps/s $\color{#d91a1a}-2.58\%$
test_step_mdp_speed[True-False-True-False-False] 33.7630μs 8.9156μs 112.1627 KOps/s 112.4408 KOps/s $\color{#d91a1a}-0.25\%$
test_step_mdp_speed[True-False-False-True-True] 59.5810μs 25.7749μs 38.7975 KOps/s 40.2173 KOps/s $\color{#d91a1a}-3.53\%$
test_step_mdp_speed[True-False-False-True-False] 44.9440μs 16.8668μs 59.2879 KOps/s 59.3122 KOps/s $\color{#d91a1a}-0.04\%$
test_step_mdp_speed[True-False-False-False-True] 44.9730μs 15.1530μs 65.9937 KOps/s 68.0743 KOps/s $\color{#d91a1a}-3.06\%$
test_step_mdp_speed[True-False-False-False-False] 32.1090μs 10.0048μs 99.9524 KOps/s 98.5754 KOps/s $\color{#35bf28}+1.40\%$
test_step_mdp_speed[False-True-True-True-True] 62.4360μs 24.3956μs 40.9909 KOps/s 41.9882 KOps/s $\color{#d91a1a}-2.38\%$
test_step_mdp_speed[False-True-True-True-False] 41.3470μs 15.8585μs 63.0578 KOps/s 64.5239 KOps/s $\color{#d91a1a}-2.27\%$
test_step_mdp_speed[False-True-True-False-True] 36.5380μs 16.1420μs 61.9504 KOps/s 63.7868 KOps/s $\color{#d91a1a}-2.88\%$
test_step_mdp_speed[False-True-True-False-False] 34.3950μs 10.2087μs 97.9555 KOps/s 100.4662 KOps/s $\color{#d91a1a}-2.50\%$
test_step_mdp_speed[False-True-False-True-True] 50.3140μs 25.9010μs 38.6086 KOps/s 39.4285 KOps/s $\color{#d91a1a}-2.08\%$
test_step_mdp_speed[False-True-False-True-False] 61.8660μs 16.9177μs 59.1097 KOps/s 59.4924 KOps/s $\color{#d91a1a}-0.64\%$
test_step_mdp_speed[False-True-False-False-True] 47.4590μs 17.2122μs 58.0983 KOps/s 58.7489 KOps/s $\color{#d91a1a}-1.11\%$
test_step_mdp_speed[False-True-False-False-False] 35.7570μs 11.2978μs 88.5131 KOps/s 89.3073 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[False-False-True-True-True] 60.8940μs 26.6683μs 37.4977 KOps/s 37.9558 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[False-False-True-True-False] 43.7420μs 18.2566μs 54.7748 KOps/s 55.2269 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[False-False-True-False-True] 58.6710μs 16.9911μs 58.8544 KOps/s 58.5065 KOps/s $\color{#35bf28}+0.59\%$
test_step_mdp_speed[False-False-True-False-False] 34.0140μs 11.2645μs 88.7742 KOps/s 90.2679 KOps/s $\color{#d91a1a}-1.65\%$
test_step_mdp_speed[False-False-False-True-True] 56.2250μs 27.5593μs 36.2854 KOps/s 36.8342 KOps/s $\color{#d91a1a}-1.49\%$
test_step_mdp_speed[False-False-False-True-False] 55.7740μs 19.1648μs 52.1789 KOps/s 51.5877 KOps/s $\color{#35bf28}+1.15\%$
test_step_mdp_speed[False-False-False-False-True] 38.7520μs 18.0254μs 55.4774 KOps/s 55.2943 KOps/s $\color{#35bf28}+0.33\%$
test_step_mdp_speed[False-False-False-False-False] 44.9840μs 12.2969μs 81.3216 KOps/s 80.9992 KOps/s $\color{#35bf28}+0.40\%$
test_values[generalized_advantage_estimate-True-True] 11.3565ms 9.4124ms 106.2425 Ops/s 107.2654 Ops/s $\color{#d91a1a}-0.95\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.1107ms 35.2630ms 28.3584 Ops/s 28.5302 Ops/s $\color{#d91a1a}-0.60\%$
test_values[td0_return_estimate-False-False] 0.2343ms 0.1767ms 5.6599 KOps/s 5.7773 KOps/s $\color{#d91a1a}-2.03\%$
test_values[td1_return_estimate-False-False] 23.7554ms 23.3670ms 42.7955 Ops/s 42.0805 Ops/s $\color{#35bf28}+1.70\%$
test_values[vec_td1_return_estimate-False-False] 37.4676ms 35.3921ms 28.2549 Ops/s 28.5053 Ops/s $\color{#d91a1a}-0.88\%$
test_values[td_lambda_return_estimate-True-False] 36.6791ms 33.8101ms 29.5769 Ops/s 29.7059 Ops/s $\color{#d91a1a}-0.43\%$
test_values[vec_td_lambda_return_estimate-True-False] 38.3437ms 35.3918ms 28.2552 Ops/s 28.3576 Ops/s $\color{#d91a1a}-0.36\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.4304ms 8.1475ms 122.7372 Ops/s 122.1078 Ops/s $\color{#35bf28}+0.52\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2618ms 1.8640ms 536.4699 Ops/s 502.6988 Ops/s $\textbf{\color{#35bf28}+6.72\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6416ms 0.3518ms 2.8425 KOps/s 2.9000 KOps/s $\color{#d91a1a}-1.98\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 45.8111ms 44.0808ms 22.6856 Ops/s 24.0782 Ops/s $\textbf{\color{#d91a1a}-5.78\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8677ms 3.0504ms 327.8296 Ops/s 325.7760 Ops/s $\color{#35bf28}+0.63\%$
test_dqn_speed 65.9930ms 1.5174ms 659.0052 Ops/s 713.8012 Ops/s $\textbf{\color{#d91a1a}-7.68\%}$
test_ddpg_speed 3.1394ms 2.8368ms 352.5144 Ops/s 344.0234 Ops/s $\color{#35bf28}+2.47\%$
test_sac_speed 10.1428ms 8.8099ms 113.5086 Ops/s 118.7645 Ops/s $\color{#d91a1a}-4.43\%$
test_redq_speed 14.7276ms 13.4039ms 74.6054 Ops/s 75.3530 Ops/s $\color{#d91a1a}-0.99\%$
test_redq_deprec_speed 17.8095ms 13.9972ms 71.4430 Ops/s 70.5461 Ops/s $\color{#35bf28}+1.27\%$
test_td3_speed 8.8136ms 8.4682ms 118.0885 Ops/s 118.0345 Ops/s $\color{#35bf28}+0.05\%$
test_cql_speed 37.2854ms 36.5560ms 27.3553 Ops/s 27.4318 Ops/s $\color{#d91a1a}-0.28\%$
test_a2c_speed 8.4185ms 7.4430ms 134.3547 Ops/s 134.8447 Ops/s $\color{#d91a1a}-0.36\%$
test_ppo_speed 8.4607ms 7.7318ms 129.3352 Ops/s 129.4637 Ops/s $\color{#d91a1a}-0.10\%$
test_reinforce_speed 7.6492ms 6.6499ms 150.3786 Ops/s 150.3858 Ops/s $-0.00\%$
test_iql_speed 33.9626ms 32.7345ms 30.5488 Ops/s 29.6175 Ops/s $\color{#35bf28}+3.14\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.0556ms 2.2312ms 448.1829 Ops/s 417.8385 Ops/s $\textbf{\color{#35bf28}+7.26\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7563ms 0.4929ms 2.0290 KOps/s 1.9921 KOps/s $\color{#35bf28}+1.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7657ms 0.4664ms 2.1440 KOps/s 2.0902 KOps/s $\color{#35bf28}+2.57\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.4380ms 2.1632ms 462.2739 Ops/s 431.1136 Ops/s $\textbf{\color{#35bf28}+7.23\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1911ms 0.4855ms 2.0597 KOps/s 2.0542 KOps/s $\color{#35bf28}+0.27\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6688ms 0.4585ms 2.1811 KOps/s 2.1578 KOps/s $\color{#35bf28}+1.08\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.4790ms 2.2881ms 437.0479 Ops/s 431.2548 Ops/s $\color{#35bf28}+1.34\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0244ms 0.6068ms 1.6480 KOps/s 1.6669 KOps/s $\color{#d91a1a}-1.13\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9133ms 0.5810ms 1.7211 KOps/s 1.7301 KOps/s $\color{#d91a1a}-0.52\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.3311ms 2.2044ms 453.6402 Ops/s 442.5536 Ops/s $\color{#35bf28}+2.51\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 88.9269ms 0.6136ms 1.6297 KOps/s 2.0082 KOps/s $\textbf{\color{#d91a1a}-18.85\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6099ms 0.4646ms 2.1524 KOps/s 2.1350 KOps/s $\color{#35bf28}+0.82\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.4527ms 2.1946ms 455.6544 Ops/s 436.7595 Ops/s $\color{#35bf28}+4.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7349ms 0.4885ms 2.0472 KOps/s 2.0079 KOps/s $\color{#35bf28}+1.96\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5744ms 0.4604ms 2.1720 KOps/s 2.1513 KOps/s $\color{#35bf28}+0.96\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4303ms 2.3153ms 431.9124 Ops/s 427.2027 Ops/s $\color{#35bf28}+1.10\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9139ms 0.6056ms 1.6514 KOps/s 1.6538 KOps/s $\color{#d91a1a}-0.14\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 3.6726ms 0.5826ms 1.7165 KOps/s 1.7211 KOps/s $\color{#d91a1a}-0.27\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1011s 5.5124ms 181.4090 Ops/s 178.4147 Ops/s $\color{#35bf28}+1.68\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.1458ms 11.9629ms 83.5915 Ops/s 84.1073 Ops/s $\color{#d91a1a}-0.61\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.7165ms 1.0314ms 969.5461 Ops/s 979.3855 Ops/s $\color{#d91a1a}-1.00\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 86.8981ms 6.8328ms 146.3535 Ops/s 143.8119 Ops/s $\color{#35bf28}+1.77\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.3604ms 11.9587ms 83.6208 Ops/s 84.4106 Ops/s $\color{#d91a1a}-0.94\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.5178ms 1.0247ms 975.9105 Ops/s 965.1147 Ops/s $\color{#35bf28}+1.12\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 86.0500ms 5.5466ms 180.2897 Ops/s 174.6044 Ops/s $\color{#35bf28}+3.26\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 95.2210ms 13.9441ms 71.7147 Ops/s 71.4021 Ops/s $\color{#35bf28}+0.44\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 1.8375ms 1.3562ms 737.3502 Ops/s 751.9264 Ops/s $\color{#d91a1a}-1.94\%$

Copy link

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}31$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1128s 0.1124s 8.8934 Ops/s 8.4204 Ops/s $\textbf{\color{#35bf28}+5.62\%}$
test_sync 96.2856ms 96.0274ms 10.4137 Ops/s 10.4209 Ops/s $\color{#d91a1a}-0.07\%$
test_async 0.1816s 91.9013ms 10.8812 Ops/s 10.9096 Ops/s $\color{#d91a1a}-0.26\%$
test_single_pixels 0.1346s 0.1344s 7.4418 Ops/s 7.0211 Ops/s $\textbf{\color{#35bf28}+5.99\%}$
test_sync_pixels 90.5821ms 82.8007ms 12.0772 Ops/s 12.3068 Ops/s $\color{#d91a1a}-1.87\%$
test_async_pixels 0.1469s 74.0587ms 13.5028 Ops/s 13.7608 Ops/s $\color{#d91a1a}-1.88\%$
test_simple 0.8778s 0.8222s 1.2162 Ops/s 1.1937 Ops/s $\color{#35bf28}+1.88\%$
test_transformed 1.0938s 1.0384s 0.9630 Ops/s 0.9235 Ops/s $\color{#35bf28}+4.28\%$
test_serial 2.4568s 2.4024s 0.4162 Ops/s 0.3962 Ops/s $\textbf{\color{#35bf28}+5.06\%}$
test_parallel 2.1605s 2.0872s 0.4791 Ops/s 0.4770 Ops/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[True-True-True-True-True] 0.1040ms 32.3170μs 30.9434 KOps/s 29.2345 KOps/s $\textbf{\color{#35bf28}+5.85\%}$
test_step_mdp_speed[True-True-True-True-False] 45.6200μs 19.3046μs 51.8011 KOps/s 48.9322 KOps/s $\textbf{\color{#35bf28}+5.86\%}$
test_step_mdp_speed[True-True-True-False-True] 40.1500μs 18.3055μs 54.6285 KOps/s 51.4647 KOps/s $\textbf{\color{#35bf28}+6.15\%}$
test_step_mdp_speed[True-True-True-False-False] 0.1028ms 10.9934μs 90.9639 KOps/s 85.8099 KOps/s $\textbf{\color{#35bf28}+6.01\%}$
test_step_mdp_speed[True-True-False-True-True] 55.3510μs 33.9039μs 29.4951 KOps/s 27.9196 KOps/s $\textbf{\color{#35bf28}+5.64\%}$
test_step_mdp_speed[True-True-False-True-False] 43.6320μs 21.1546μs 47.2711 KOps/s 44.8067 KOps/s $\textbf{\color{#35bf28}+5.50\%}$
test_step_mdp_speed[True-True-False-False-True] 40.7500μs 20.0318μs 49.9207 KOps/s 47.0103 KOps/s $\textbf{\color{#35bf28}+6.19\%}$
test_step_mdp_speed[True-True-False-False-False] 39.1210μs 12.9739μs 77.0781 KOps/s 74.3747 KOps/s $\color{#35bf28}+3.63\%$
test_step_mdp_speed[True-False-True-True-True] 50.8710μs 35.9035μs 27.8524 KOps/s 26.0447 KOps/s $\textbf{\color{#35bf28}+6.94\%}$
test_step_mdp_speed[True-False-True-True-False] 40.0910μs 23.1530μs 43.1909 KOps/s 40.7633 KOps/s $\textbf{\color{#35bf28}+5.96\%}$
test_step_mdp_speed[True-False-True-False-True] 38.9210μs 19.6577μs 50.8706 KOps/s 47.2215 KOps/s $\textbf{\color{#35bf28}+7.73\%}$
test_step_mdp_speed[True-False-True-False-False] 33.2610μs 12.9837μs 77.0194 KOps/s 74.5202 KOps/s $\color{#35bf28}+3.35\%$
test_step_mdp_speed[True-False-False-True-True] 63.9110μs 37.9287μs 26.3652 KOps/s 24.8447 KOps/s $\textbf{\color{#35bf28}+6.12\%}$
test_step_mdp_speed[True-False-False-True-False] 47.0900μs 25.0531μs 39.9153 KOps/s 37.9743 KOps/s $\textbf{\color{#35bf28}+5.11\%}$
test_step_mdp_speed[True-False-False-False-True] 38.9310μs 21.8569μs 45.7521 KOps/s 43.4040 KOps/s $\textbf{\color{#35bf28}+5.41\%}$
test_step_mdp_speed[True-False-False-False-False] 32.2410μs 14.7950μs 67.5905 KOps/s 65.3375 KOps/s $\color{#35bf28}+3.45\%$
test_step_mdp_speed[False-True-True-True-True] 67.7210μs 35.9359μs 27.8273 KOps/s 26.0951 KOps/s $\textbf{\color{#35bf28}+6.64\%}$
test_step_mdp_speed[False-True-True-True-False] 49.2710μs 23.5798μs 42.4091 KOps/s 40.8027 KOps/s $\color{#35bf28}+3.94\%$
test_step_mdp_speed[False-True-True-False-True] 45.4710μs 24.4573μs 40.8876 KOps/s 39.1135 KOps/s $\color{#35bf28}+4.54\%$
test_step_mdp_speed[False-True-True-False-False] 31.7800μs 14.7362μs 67.8601 KOps/s 64.1914 KOps/s $\textbf{\color{#35bf28}+5.72\%}$
test_step_mdp_speed[False-True-False-True-True] 70.2110μs 37.6274μs 26.5764 KOps/s 25.1714 KOps/s $\textbf{\color{#35bf28}+5.58\%}$
test_step_mdp_speed[False-True-False-True-False] 91.4110μs 24.7384μs 40.4230 KOps/s 37.5512 KOps/s $\textbf{\color{#35bf28}+7.65\%}$
test_step_mdp_speed[False-True-False-False-True] 51.8320μs 25.6703μs 38.9556 KOps/s 36.7455 KOps/s $\textbf{\color{#35bf28}+6.01\%}$
test_step_mdp_speed[False-True-False-False-False] 41.1720μs 16.4112μs 60.9341 KOps/s 56.8308 KOps/s $\textbf{\color{#35bf28}+7.22\%}$
test_step_mdp_speed[False-False-True-True-True] 61.8410μs 39.0316μs 25.6203 KOps/s 23.8406 KOps/s $\textbf{\color{#35bf28}+7.46\%}$
test_step_mdp_speed[False-False-True-True-False] 42.7810μs 26.6280μs 37.5545 KOps/s 35.0988 KOps/s $\textbf{\color{#35bf28}+7.00\%}$
test_step_mdp_speed[False-False-True-False-True] 43.9610μs 25.8211μs 38.7280 KOps/s 37.3296 KOps/s $\color{#35bf28}+3.75\%$
test_step_mdp_speed[False-False-True-False-False] 34.5710μs 16.3934μs 61.0003 KOps/s 57.3005 KOps/s $\textbf{\color{#35bf28}+6.46\%}$
test_step_mdp_speed[False-False-False-True-True] 62.1010μs 41.3410μs 24.1891 KOps/s 23.1163 KOps/s $\color{#35bf28}+4.64\%$
test_step_mdp_speed[False-False-False-True-False] 54.4420μs 28.5687μs 35.0033 KOps/s 33.0587 KOps/s $\textbf{\color{#35bf28}+5.88\%}$
test_step_mdp_speed[False-False-False-False-True] 44.6710μs 27.4374μs 36.4466 KOps/s 34.4147 KOps/s $\textbf{\color{#35bf28}+5.90\%}$
test_step_mdp_speed[False-False-False-False-False] 32.1610μs 18.1902μs 54.9745 KOps/s 51.9640 KOps/s $\textbf{\color{#35bf28}+5.79\%}$
test_values[generalized_advantage_estimate-True-True] 24.9094ms 24.3948ms 40.9924 Ops/s 40.0853 Ops/s $\color{#35bf28}+2.26\%$
test_values[vec_generalized_advantage_estimate-True-True] 84.8205ms 3.2517ms 307.5339 Ops/s 309.1991 Ops/s $\color{#d91a1a}-0.54\%$
test_values[td0_return_estimate-False-False] 97.0120μs 60.2393μs 16.6004 KOps/s 16.2198 KOps/s $\color{#35bf28}+2.35\%$
test_values[td1_return_estimate-False-False] 55.1709ms 54.8931ms 18.2172 Ops/s 18.7187 Ops/s $\color{#d91a1a}-2.68\%$
test_values[vec_td1_return_estimate-False-False] 2.0379ms 1.7504ms 571.3099 Ops/s 566.1239 Ops/s $\color{#35bf28}+0.92\%$
test_values[td_lambda_return_estimate-True-False] 83.7838ms 83.3161ms 12.0025 Ops/s 11.7981 Ops/s $\color{#35bf28}+1.73\%$
test_values[vec_td_lambda_return_estimate-True-False] 3.9823ms 1.7872ms 559.5398 Ops/s 554.7098 Ops/s $\color{#35bf28}+0.87\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.3111ms 23.8836ms 41.8697 Ops/s 41.9739 Ops/s $\color{#d91a1a}-0.25\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8896ms 0.6903ms 1.4487 KOps/s 1.4036 KOps/s $\color{#35bf28}+3.21\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6973ms 0.6426ms 1.5561 KOps/s 1.5208 KOps/s $\color{#35bf28}+2.32\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.4780ms 1.4449ms 692.0808 Ops/s 682.9940 Ops/s $\color{#35bf28}+1.33\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9634ms 0.6625ms 1.5093 KOps/s 1.4723 KOps/s $\color{#35bf28}+2.52\%$
test_dqn_speed 8.4656ms 1.4776ms 676.7724 Ops/s 662.8045 Ops/s $\color{#35bf28}+2.11\%$
test_ddpg_speed 3.2470ms 2.8406ms 352.0394 Ops/s 345.0701 Ops/s $\color{#35bf28}+2.02\%$
test_sac_speed 8.6829ms 8.1792ms 122.2609 Ops/s 120.1194 Ops/s $\color{#35bf28}+1.78\%$
test_redq_speed 11.0795ms 10.2885ms 97.1955 Ops/s 96.1274 Ops/s $\color{#35bf28}+1.11\%$
test_redq_deprec_speed 12.0721ms 11.2523ms 88.8703 Ops/s 87.7014 Ops/s $\color{#35bf28}+1.33\%$
test_td3_speed 15.9048ms 8.2432ms 121.3128 Ops/s 119.8984 Ops/s $\color{#35bf28}+1.18\%$
test_cql_speed 27.2469ms 25.5088ms 39.2022 Ops/s 38.6569 Ops/s $\color{#35bf28}+1.41\%$
test_a2c_speed 5.7544ms 5.4444ms 183.6766 Ops/s 177.0239 Ops/s $\color{#35bf28}+3.76\%$
test_ppo_speed 6.2143ms 5.7952ms 172.5572 Ops/s 166.7885 Ops/s $\color{#35bf28}+3.46\%$
test_reinforce_speed 4.7904ms 4.4866ms 222.8868 Ops/s 217.1989 Ops/s $\color{#35bf28}+2.62\%$
test_iql_speed 19.9187ms 19.4568ms 51.3960 Ops/s 50.0638 Ops/s $\color{#35bf28}+2.66\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.9258ms 2.8341ms 352.8414 Ops/s 347.8872 Ops/s $\color{#35bf28}+1.42\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 89.5719ms 0.6087ms 1.6429 KOps/s 1.8418 KOps/s $\textbf{\color{#d91a1a}-10.80\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6941ms 0.5142ms 1.9447 KOps/s 1.9299 KOps/s $\color{#35bf28}+0.77\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.0076ms 2.8682ms 348.6557 Ops/s 345.5638 Ops/s $\color{#35bf28}+0.89\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2641ms 0.5301ms 1.8864 KOps/s 1.8735 KOps/s $\color{#35bf28}+0.69\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6517ms 0.5076ms 1.9701 KOps/s 1.9572 KOps/s $\color{#35bf28}+0.66\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1032ms 2.9617ms 337.6468 Ops/s 332.4206 Ops/s $\color{#35bf28}+1.57\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3620ms 0.6622ms 1.5102 KOps/s 1.5076 KOps/s $\color{#35bf28}+0.17\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7981ms 0.6450ms 1.5504 KOps/s 1.3738 KOps/s $\textbf{\color{#35bf28}+12.86\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.9875ms 2.8535ms 350.4510 Ops/s 347.6513 Ops/s $\color{#35bf28}+0.81\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1640ms 0.5364ms 1.8644 KOps/s 1.8310 KOps/s $\color{#35bf28}+1.82\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7182ms 0.5141ms 1.9451 KOps/s 1.9271 KOps/s $\color{#35bf28}+0.94\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.2150ms 2.8700ms 348.4260 Ops/s 348.9060 Ops/s $\color{#d91a1a}-0.14\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2493ms 0.5302ms 1.8860 KOps/s 1.5658 KOps/s $\textbf{\color{#35bf28}+20.45\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6519ms 0.5093ms 1.9636 KOps/s 1.9578 KOps/s $\color{#35bf28}+0.30\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.0885ms 2.9761ms 336.0131 Ops/s 332.4440 Ops/s $\color{#35bf28}+1.07\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2585ms 0.6672ms 1.4987 KOps/s 1.4820 KOps/s $\color{#35bf28}+1.13\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8349ms 0.6465ms 1.5468 KOps/s 1.5437 KOps/s $\color{#35bf28}+0.20\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1186s 8.7947ms 113.7043 Ops/s 115.6100 Ops/s $\color{#d91a1a}-1.65\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.8069ms 14.4246ms 69.3261 Ops/s 66.6029 Ops/s $\color{#35bf28}+4.09\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.4335ms 1.1818ms 846.1826 Ops/s 860.7821 Ops/s $\color{#d91a1a}-1.70\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 98.3857ms 6.5441ms 152.8093 Ops/s 151.1961 Ops/s $\color{#35bf28}+1.07\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.1097s 16.3334ms 61.2242 Ops/s 59.5252 Ops/s $\color{#35bf28}+2.85\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.3312ms 1.2709ms 786.8277 Ops/s 877.5365 Ops/s $\textbf{\color{#d91a1a}-10.34\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 99.3007ms 6.9195ms 144.5181 Ops/s 142.0899 Ops/s $\color{#35bf28}+1.71\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 16.9631ms 14.5070ms 68.9320 Ops/s 65.0852 Ops/s $\textbf{\color{#35bf28}+5.91\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.6815ms 1.6274ms 614.4950 Ops/s 622.6801 Ops/s $\color{#d91a1a}-1.31\%$

@vmoens vmoens merged commit 3df6d9f into main Feb 25, 2024
66 of 68 checks passed
@vmoens vmoens deleted the fix-catframes-pixels branch February 25, 2024 00:53
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. Suitable for minor Suitable to be integrated in minor release (no new feature)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants