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

[Feature] habitat env from config #2539

Open
wants to merge 10 commits into
base: main
Choose a base branch
from
Open

[Feature] habitat env from config #2539

wants to merge 10 commits into from
+41 −12

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Nov 6, 2024

Description

Describe your changes in detail.

Motivation and Context

Why is this change required? What problem does it solve?
If it fixes an open issue, please link to the issue here.
You can use the syntax close #15213 if this solves the issue #15213

  • I have raised an issue to propose this change (required for new features and bug fixes)

Types of changes

What types of changes does your code introduce? Remove all that do not apply:

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds core functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation (update in the documentation)
  • Example (update in the folder of examples)

Checklist

Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!

  • I have read the CONTRIBUTION guide (required)
  • My change requires a change to the documentation.
  • I have updated the tests accordingly (required for a bug fix or a new feature).
  • I have updated the documentation accordingly.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Nov 6, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2539

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

❌ 13 New Failures, 1 Cancelled Job, 2 Unrelated Failures

As of commit 19ae46a with merge base 594462d (image):

NEW FAILURES - The following jobs have failed:

CANCELLED JOB - The following job was cancelled. Please retry:

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 Nov 6, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Nov 6, 2024 •
edited
Loading

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}10$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4340s 0.4304s 2.3236 Ops/s 2.1880 Ops/s $\textbf{\color{#35bf28}+6.19\%}$
test_transformed 0.7143s 0.6344s 1.5764 Ops/s 1.6302 Ops/s $\color{#d91a1a}-3.30\%$
test_serial 1.3529s 1.3434s 0.7444 Ops/s 0.7346 Ops/s $\color{#35bf28}+1.34\%$
test_parallel 1.2932s 1.2818s 0.7802 Ops/s 0.7473 Ops/s $\color{#35bf28}+4.40\%$
test_step_mdp_speed[True-True-True-True-True] 0.1801ms 29.9612μs 33.3765 KOps/s 33.3648 KOps/s $\color{#35bf28}+0.04\%$
test_step_mdp_speed[True-True-True-True-False] 48.9520μs 17.4546μs 57.2914 KOps/s 56.8933 KOps/s $\color{#35bf28}+0.70\%$
test_step_mdp_speed[True-True-True-False-True] 44.4540μs 16.8241μs 59.4387 KOps/s 59.9248 KOps/s $\color{#d91a1a}-0.81\%$
test_step_mdp_speed[True-True-True-False-False] 44.7140μs 10.1339μs 98.6789 KOps/s 101.5415 KOps/s $\color{#d91a1a}-2.82\%$
test_step_mdp_speed[True-True-False-True-True] 67.1260μs 31.9505μs 31.2984 KOps/s 32.0433 KOps/s $\color{#d91a1a}-2.32\%$
test_step_mdp_speed[True-True-False-True-False] 51.0870μs 19.6211μs 50.9655 KOps/s 51.9486 KOps/s $\color{#d91a1a}-1.89\%$
test_step_mdp_speed[True-True-False-False-True] 59.2820μs 18.6787μs 53.5370 KOps/s 54.1519 KOps/s $\color{#d91a1a}-1.14\%$
test_step_mdp_speed[True-True-False-False-False] 61.6360μs 11.8510μs 84.3808 KOps/s 86.6108 KOps/s $\color{#d91a1a}-2.57\%$
test_step_mdp_speed[True-False-True-True-True] 73.4080μs 33.4172μs 29.9247 KOps/s 29.3217 KOps/s $\color{#35bf28}+2.06\%$
test_step_mdp_speed[True-False-True-True-False] 60.9140μs 21.0775μs 47.4440 KOps/s 47.2199 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[True-False-True-False-True] 57.8690μs 18.8488μs 53.0538 KOps/s 54.0471 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[True-False-True-False-False] 60.3430μs 11.6164μs 86.0852 KOps/s 86.1284 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[True-False-False-True-True] 79.0050μs 35.1037μs 28.4870 KOps/s 28.2686 KOps/s $\color{#35bf28}+0.77\%$
test_step_mdp_speed[True-False-False-True-False] 53.7020μs 22.7671μs 43.9230 KOps/s 43.4925 KOps/s $\color{#35bf28}+0.99\%$
test_step_mdp_speed[True-False-False-False-True] 56.7270μs 20.3535μs 49.1316 KOps/s 49.5348 KOps/s $\color{#d91a1a}-0.81\%$
test_step_mdp_speed[True-False-False-False-False] 42.7500μs 13.4757μs 74.2075 KOps/s 74.8479 KOps/s $\color{#d91a1a}-0.86\%$
test_step_mdp_speed[False-True-True-True-True] 74.9710μs 33.7410μs 29.6376 KOps/s 29.8689 KOps/s $\color{#d91a1a}-0.77\%$
test_step_mdp_speed[False-True-True-True-False] 51.0860μs 21.2492μs 47.0605 KOps/s 47.2735 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[False-True-True-False-True] 92.6940μs 20.9732μs 47.6798 KOps/s 47.1710 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[False-True-True-False-False] 36.7390μs 13.0788μs 76.4593 KOps/s 77.2489 KOps/s $\color{#d91a1a}-1.02\%$
test_step_mdp_speed[False-True-False-True-True] 68.5490μs 35.5638μs 28.1184 KOps/s 28.4176 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[False-True-False-True-False] 64.3010μs 23.2170μs 43.0719 KOps/s 43.5349 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-True-False-False-True] 2.9692ms 22.8698μs 43.7258 KOps/s 44.3102 KOps/s $\color{#d91a1a}-1.32\%$
test_step_mdp_speed[False-True-False-False-False] 51.9770μs 14.7646μs 67.7296 KOps/s 68.0754 KOps/s $\color{#d91a1a}-0.51\%$
test_step_mdp_speed[False-False-True-True-True] 90.5500μs 36.5701μs 27.3447 KOps/s 27.0441 KOps/s $\color{#35bf28}+1.11\%$
test_step_mdp_speed[False-False-True-True-False] 72.0850μs 24.6134μs 40.6282 KOps/s 40.2506 KOps/s $\color{#35bf28}+0.94\%$
test_step_mdp_speed[False-False-True-False-True] 56.1950μs 22.7682μs 43.9210 KOps/s 44.1829 KOps/s $\color{#d91a1a}-0.59\%$
test_step_mdp_speed[False-False-True-False-False] 64.8220μs 14.6844μs 68.0993 KOps/s 68.1151 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[False-False-False-True-True] 96.1310μs 38.3934μs 26.0461 KOps/s 26.0029 KOps/s $\color{#35bf28}+0.17\%$
test_step_mdp_speed[False-False-False-True-False] 60.4540μs 26.3140μs 38.0026 KOps/s 38.0842 KOps/s $\color{#d91a1a}-0.21\%$
test_step_mdp_speed[False-False-False-False-True] 57.7780μs 24.1414μs 41.4226 KOps/s 40.6512 KOps/s $\color{#35bf28}+1.90\%$
test_step_mdp_speed[False-False-False-False-False] 39.5050μs 16.3182μs 61.2811 KOps/s 61.3020 KOps/s $\color{#d91a1a}-0.03\%$
test_values[generalized_advantage_estimate-True-True] 12.5065ms 9.5674ms 104.5214 Ops/s 107.1451 Ops/s $\color{#d91a1a}-2.45\%$
test_values[vec_generalized_advantage_estimate-True-True] 49.5090ms 34.9070ms 28.6475 Ops/s 29.5638 Ops/s $\color{#d91a1a}-3.10\%$
test_values[td0_return_estimate-False-False] 0.2540ms 0.1960ms 5.1028 KOps/s 5.6657 KOps/s $\textbf{\color{#d91a1a}-9.94\%}$
test_values[td1_return_estimate-False-False] 24.2413ms 23.9302ms 41.7882 Ops/s 42.2037 Ops/s $\color{#d91a1a}-0.98\%$
test_values[vec_td1_return_estimate-False-False] 36.9259ms 34.3213ms 29.1364 Ops/s 29.6077 Ops/s $\color{#d91a1a}-1.59\%$
test_values[td_lambda_return_estimate-True-False] 38.5589ms 34.0666ms 29.3543 Ops/s 29.4391 Ops/s $\color{#d91a1a}-0.29\%$
test_values[vec_td_lambda_return_estimate-True-False] 36.6938ms 34.1048ms 29.3214 Ops/s 29.0541 Ops/s $\color{#35bf28}+0.92\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.5760ms 8.3484ms 119.7838 Ops/s 120.9197 Ops/s $\color{#d91a1a}-0.94\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3870ms 1.9481ms 513.3188 Ops/s 491.9783 Ops/s $\color{#35bf28}+4.34\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5815ms 0.3665ms 2.7285 KOps/s 2.4442 KOps/s $\textbf{\color{#35bf28}+11.63\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 44.0872ms 42.1381ms 23.7315 Ops/s 22.3471 Ops/s $\textbf{\color{#35bf28}+6.20\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.7089ms 3.0510ms 327.7562 Ops/s 327.0843 Ops/s $\color{#35bf28}+0.21\%$
test_dqn_speed[False-None] 1.9328ms 1.4123ms 708.0663 Ops/s 702.7030 Ops/s $\color{#35bf28}+0.76\%$
test_dqn_speed[False-backward] 2.0627ms 1.9419ms 514.9658 Ops/s 528.0520 Ops/s $\color{#d91a1a}-2.48\%$
test_dqn_speed[True-None] 0.6736ms 0.4736ms 2.1117 KOps/s 2.1371 KOps/s $\color{#d91a1a}-1.19\%$
test_dqn_speed[True-backward] 0.9802ms 0.9200ms 1.0869 KOps/s 1.0780 KOps/s $\color{#35bf28}+0.83\%$
test_dqn_speed[reduce-overhead-None] 1.9136ms 0.4709ms 2.1234 KOps/s 2.1133 KOps/s $\color{#35bf28}+0.48\%$
test_dqn_speed[reduce-overhead-backward] 1.2104ms 0.9444ms 1.0589 KOps/s 1.1103 KOps/s $\color{#d91a1a}-4.63\%$
test_ddpg_speed[False-None] 3.5457ms 2.9024ms 344.5416 Ops/s 341.5923 Ops/s $\color{#35bf28}+0.86\%$
test_ddpg_speed[False-backward] 4.8844ms 4.0879ms 244.6224 Ops/s 246.9228 Ops/s $\color{#d91a1a}-0.93\%$
test_ddpg_speed[True-None] 1.2572ms 1.0135ms 986.6897 Ops/s 991.9007 Ops/s $\color{#d91a1a}-0.53\%$
test_ddpg_speed[True-backward] 2.0065ms 1.9034ms 525.3630 Ops/s 524.3667 Ops/s $\color{#35bf28}+0.19\%$
test_ddpg_speed[reduce-overhead-None] 1.3767ms 1.0083ms 991.7208 Ops/s 987.0941 Ops/s $\color{#35bf28}+0.47\%$
test_ddpg_speed[reduce-overhead-backward] 1.9690ms 1.9010ms 526.0481 Ops/s 527.0808 Ops/s $\color{#d91a1a}-0.20\%$
test_sac_speed[False-None] 9.7017ms 8.1759ms 122.3105 Ops/s 121.7039 Ops/s $\color{#35bf28}+0.50\%$
test_sac_speed[False-backward] 11.8567ms 10.9196ms 91.5787 Ops/s 90.9547 Ops/s $\color{#35bf28}+0.69\%$
test_sac_speed[True-None] 2.4329ms 1.8372ms 544.3165 Ops/s 546.2913 Ops/s $\color{#d91a1a}-0.36\%$
test_sac_speed[True-backward] 3.8553ms 3.5421ms 282.3167 Ops/s 283.9557 Ops/s $\color{#d91a1a}-0.58\%$
test_sac_speed[reduce-overhead-None] 2.8602ms 1.8505ms 540.3887 Ops/s 544.7904 Ops/s $\color{#d91a1a}-0.81\%$
test_sac_speed[reduce-overhead-backward] 3.5798ms 3.5226ms 283.8777 Ops/s 260.6804 Ops/s $\textbf{\color{#35bf28}+8.90\%}$
test_redq_speed[False-None] 14.4280ms 12.9920ms 76.9706 Ops/s 74.4983 Ops/s $\color{#35bf28}+3.32\%$
test_redq_speed[False-backward] 23.2904ms 22.2048ms 45.0353 Ops/s 43.5382 Ops/s $\color{#35bf28}+3.44\%$
test_redq_speed[True-None] 5.1720ms 4.5659ms 219.0158 Ops/s 207.2229 Ops/s $\textbf{\color{#35bf28}+5.69\%}$
test_redq_speed[True-backward] 13.4716ms 12.3920ms 80.6974 Ops/s 77.1716 Ops/s $\color{#35bf28}+4.57\%$
test_redq_speed[reduce-overhead-None] 5.5332ms 4.7488ms 210.5787 Ops/s 207.5834 Ops/s $\color{#35bf28}+1.44\%$
test_redq_speed[reduce-overhead-backward] 12.8426ms 12.4142ms 80.5530 Ops/s 82.4836 Ops/s $\color{#d91a1a}-2.34\%$
test_redq_deprec_speed[False-None] 14.5413ms 13.2020ms 75.7460 Ops/s 75.2844 Ops/s $\color{#35bf28}+0.61\%$
test_redq_deprec_speed[False-backward] 21.7001ms 18.9451ms 52.7842 Ops/s 52.5182 Ops/s $\color{#35bf28}+0.51\%$
test_redq_deprec_speed[True-None] 4.3927ms 3.6033ms 277.5201 Ops/s 278.7693 Ops/s $\color{#d91a1a}-0.45\%$
test_redq_deprec_speed[True-backward] 9.3192ms 8.4504ms 118.3379 Ops/s 122.7696 Ops/s $\color{#d91a1a}-3.61\%$
test_redq_deprec_speed[reduce-overhead-None] 4.7546ms 3.7655ms 265.5708 Ops/s 279.8046 Ops/s $\textbf{\color{#d91a1a}-5.09\%}$
test_redq_deprec_speed[reduce-overhead-backward] 8.5079ms 8.0794ms 123.7722 Ops/s 124.0614 Ops/s $\color{#d91a1a}-0.23\%$
test_td3_speed[False-None] 8.2614ms 7.9920ms 125.1249 Ops/s 121.9234 Ops/s $\color{#35bf28}+2.63\%$
test_td3_speed[False-backward] 12.1911ms 10.5197ms 95.0594 Ops/s 93.1513 Ops/s $\color{#35bf28}+2.05\%$
test_td3_speed[True-None] 2.1827ms 1.7152ms 583.0102 Ops/s 578.3008 Ops/s $\color{#35bf28}+0.81\%$
test_td3_speed[True-backward] 3.4032ms 3.3103ms 302.0852 Ops/s 295.4701 Ops/s $\color{#35bf28}+2.24\%$
test_td3_speed[reduce-overhead-None] 1.9306ms 1.7152ms 583.0378 Ops/s 579.0073 Ops/s $\color{#35bf28}+0.70\%$
test_td3_speed[reduce-overhead-backward] 3.4886ms 3.3290ms 300.3868 Ops/s 296.6372 Ops/s $\color{#35bf28}+1.26\%$
test_cql_speed[False-None] 39.2527ms 35.8730ms 27.8761 Ops/s 26.9403 Ops/s $\color{#35bf28}+3.47\%$
test_cql_speed[False-backward] 0.3055s 51.7980ms 19.3058 Ops/s 21.1802 Ops/s $\textbf{\color{#d91a1a}-8.85\%}$
test_cql_speed[True-None] 17.5653ms 15.8827ms 62.9617 Ops/s 62.2047 Ops/s $\color{#35bf28}+1.22\%$
test_cql_speed[True-backward] 23.6435ms 22.5387ms 44.3682 Ops/s 42.3394 Ops/s $\color{#35bf28}+4.79\%$
test_cql_speed[reduce-overhead-None] 17.6149ms 16.2973ms 61.3600 Ops/s 63.1282 Ops/s $\color{#d91a1a}-2.80\%$
test_cql_speed[reduce-overhead-backward] 23.6469ms 22.4241ms 44.5948 Ops/s 43.9359 Ops/s $\color{#35bf28}+1.50\%$
test_a2c_speed[False-None] 8.9226ms 7.2884ms 137.2052 Ops/s 137.1392 Ops/s $\color{#35bf28}+0.05\%$
test_a2c_speed[False-backward] 16.2373ms 14.8359ms 67.4041 Ops/s 68.0353 Ops/s $\color{#d91a1a}-0.93\%$
test_a2c_speed[True-None] 4.6087ms 4.2215ms 236.8845 Ops/s 223.2466 Ops/s $\textbf{\color{#35bf28}+6.11\%}$
test_a2c_speed[True-backward] 11.9011ms 10.7761ms 92.7977 Ops/s 91.3200 Ops/s $\color{#35bf28}+1.62\%$
test_a2c_speed[reduce-overhead-None] 5.0610ms 4.2171ms 237.1318 Ops/s 236.4753 Ops/s $\color{#35bf28}+0.28\%$
test_a2c_speed[reduce-overhead-backward] 11.5539ms 10.9523ms 91.3047 Ops/s 92.5560 Ops/s $\color{#d91a1a}-1.35\%$
test_ppo_speed[False-None] 9.3175ms 7.4855ms 133.5910 Ops/s 132.8588 Ops/s $\color{#35bf28}+0.55\%$
test_ppo_speed[False-backward] 15.7419ms 14.8143ms 67.5023 Ops/s 67.3791 Ops/s $\color{#35bf28}+0.18\%$
test_ppo_speed[True-None] 4.4479ms 3.7075ms 269.7247 Ops/s 266.0847 Ops/s $\color{#35bf28}+1.37\%$
test_ppo_speed[True-backward] 10.1258ms 9.6273ms 103.8713 Ops/s 104.3544 Ops/s $\color{#d91a1a}-0.46\%$
test_ppo_speed[reduce-overhead-None] 4.1037ms 3.6969ms 270.4980 Ops/s 269.7192 Ops/s $\color{#35bf28}+0.29\%$
test_ppo_speed[reduce-overhead-backward] 10.0313ms 9.6459ms 103.6705 Ops/s 103.5864 Ops/s $\color{#35bf28}+0.08\%$
test_reinforce_speed[False-None] 7.8053ms 6.5326ms 153.0782 Ops/s 152.0076 Ops/s $\color{#35bf28}+0.70\%$
test_reinforce_speed[False-backward] 11.6472ms 9.8240ms 101.7910 Ops/s 101.2152 Ops/s $\color{#35bf28}+0.57\%$
test_reinforce_speed[True-None] 3.5289ms 2.8210ms 354.4874 Ops/s 373.8443 Ops/s $\textbf{\color{#d91a1a}-5.18\%}$
test_reinforce_speed[True-backward] 9.8771ms 8.9285ms 112.0007 Ops/s 115.2075 Ops/s $\color{#d91a1a}-2.78\%$
test_reinforce_speed[reduce-overhead-None] 4.6985ms 2.6812ms 372.9642 Ops/s 375.8021 Ops/s $\color{#d91a1a}-0.76\%$
test_reinforce_speed[reduce-overhead-backward] 9.6445ms 8.7859ms 113.8187 Ops/s 116.3183 Ops/s $\color{#d91a1a}-2.15\%$
test_iql_speed[False-None] 33.5072ms 32.1221ms 31.1312 Ops/s 30.6135 Ops/s $\color{#35bf28}+1.69\%$
test_iql_speed[False-backward] 46.7862ms 45.4400ms 22.0070 Ops/s 21.8633 Ops/s $\color{#35bf28}+0.66\%$
test_iql_speed[True-None] 11.9522ms 10.9499ms 91.3247 Ops/s 92.4777 Ops/s $\color{#d91a1a}-1.25\%$
test_iql_speed[True-backward] 23.1034ms 21.7703ms 45.9342 Ops/s 44.1476 Ops/s $\color{#35bf28}+4.05\%$
test_iql_speed[reduce-overhead-None] 12.0456ms 10.9947ms 90.9530 Ops/s 92.7024 Ops/s $\color{#d91a1a}-1.89\%$
test_iql_speed[reduce-overhead-backward] 22.9725ms 21.9739ms 45.5085 Ops/s 45.7074 Ops/s $\color{#d91a1a}-0.44\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.3017ms 5.0071ms 199.7146 Ops/s 199.5761 Ops/s $\color{#35bf28}+0.07\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1540ms 0.5500ms 1.8181 KOps/s 1.9123 KOps/s $\color{#d91a1a}-4.92\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7647ms 0.4923ms 2.0313 KOps/s 2.0579 KOps/s $\color{#d91a1a}-1.29\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.1826ms 4.8382ms 206.6869 Ops/s 205.6290 Ops/s $\color{#35bf28}+0.51\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 3.1204ms 0.5012ms 1.9952 KOps/s 1.9814 KOps/s $\color{#35bf28}+0.69\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6999ms 0.4744ms 2.1081 KOps/s 2.0814 KOps/s $\color{#35bf28}+1.29\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.2915ms 1.6329ms 612.3959 Ops/s 610.8127 Ops/s $\color{#35bf28}+0.26\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.2488ms 1.5856ms 630.6588 Ops/s 624.7393 Ops/s $\color{#35bf28}+0.95\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.3980ms 4.9627ms 201.5037 Ops/s 196.7217 Ops/s $\color{#35bf28}+2.43\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.9718ms 0.6500ms 1.5385 KOps/s 1.5385 KOps/s $+0.00\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8437ms 0.6188ms 1.6161 KOps/s 1.6040 KOps/s $\color{#35bf28}+0.75\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.9160ms 4.7193ms 211.8947 Ops/s 206.4154 Ops/s $\color{#35bf28}+2.65\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8743ms 0.5181ms 1.9300 KOps/s 1.9625 KOps/s $\color{#d91a1a}-1.66\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 8.6390ms 0.5062ms 1.9756 KOps/s 1.6628 KOps/s $\textbf{\color{#35bf28}+18.81\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.4848ms 4.7235ms 211.7092 Ops/s 210.0686 Ops/s $\color{#35bf28}+0.78\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1423ms 0.5037ms 1.9851 KOps/s 1.9783 KOps/s $\color{#35bf28}+0.35\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7096ms 0.4750ms 2.1053 KOps/s 2.1268 KOps/s $\color{#d91a1a}-1.01\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.9850ms 4.9536ms 201.8739 Ops/s 201.1710 Ops/s $\color{#35bf28}+0.35\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.4170s 1.2395ms 806.7698 Ops/s 1.5131 KOps/s $\textbf{\color{#d91a1a}-46.68\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8249ms 0.6175ms 1.6195 KOps/s 1.6088 KOps/s $\color{#35bf28}+0.66\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.3433ms 4.1462ms 241.1844 Ops/s 247.3224 Ops/s $\color{#d91a1a}-2.48\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 5.8513ms 2.3470ms 426.0770 Ops/s 433.0663 Ops/s $\color{#d91a1a}-1.61\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.6486ms 1.3171ms 759.2320 Ops/s 781.2608 Ops/s $\color{#d91a1a}-2.82\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.3869s 11.8321ms 84.5158 Ops/s 238.8586 Ops/s $\textbf{\color{#d91a1a}-64.62\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 6.9785ms 2.2257ms 449.2887 Ops/s 441.0082 Ops/s $\color{#35bf28}+1.88\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.8230ms 1.2966ms 771.2700 Ops/s 833.4064 Ops/s $\textbf{\color{#d91a1a}-7.46\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 8.2365ms 4.4090ms 226.8112 Ops/s 34.3881 Ops/s $\textbf{\color{#35bf28}+559.56\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 6.7623ms 2.4263ms 412.1500 Ops/s 436.5221 Ops/s $\textbf{\color{#d91a1a}-5.58\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.9988ms 1.4425ms 693.2531 Ops/s 644.4551 Ops/s $\textbf{\color{#35bf28}+7.57\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.3104ms 10.9038ms 91.7110 Ops/s 86.1894 Ops/s $\textbf{\color{#35bf28}+6.41\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 14.9685ms 14.4238ms 69.3297 Ops/s 69.1766 Ops/s $\color{#35bf28}+0.22\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 20.4200ms 19.5359ms 51.1878 Ops/s 49.3265 Ops/s $\color{#35bf28}+3.77\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 15.6801ms 14.4918ms 69.0046 Ops/s 68.3295 Ops/s $\color{#35bf28}+0.99\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 21.2495ms 19.8494ms 50.3793 Ops/s 49.6317 Ops/s $\color{#35bf28}+1.51\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 16.5979ms 15.6243ms 64.0028 Ops/s 62.5927 Ops/s $\color{#35bf28}+2.25\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Nov 6, 2024 •
edited
Loading

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}18$. Worsened: $\large\color{#d91a1a}11$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7629s 0.7554s 1.3238 Ops/s 1.2939 Ops/s $\color{#35bf28}+2.31\%$
test_transformed 1.1062s 1.0319s 0.9691 Ops/s 0.9989 Ops/s $\color{#d91a1a}-2.99\%$
test_serial 2.2472s 2.1810s 0.4585 Ops/s 0.4679 Ops/s $\color{#d91a1a}-2.02\%$
test_parallel 2.1230s 1.9939s 0.5015 Ops/s 0.5001 Ops/s $\color{#35bf28}+0.28\%$
test_step_mdp_speed[True-True-True-True-True] 0.2453ms 40.4443μs 24.7254 KOps/s 24.5690 KOps/s $\color{#35bf28}+0.64\%$
test_step_mdp_speed[True-True-True-True-False] 52.4110μs 22.9457μs 43.5812 KOps/s 43.5835 KOps/s $-0.01\%$
test_step_mdp_speed[True-True-True-False-True] 57.9010μs 22.1464μs 45.1540 KOps/s 44.5317 KOps/s $\color{#35bf28}+1.40\%$
test_step_mdp_speed[True-True-True-False-False] 39.1310μs 12.8606μs 77.7570 KOps/s 77.9637 KOps/s $\color{#d91a1a}-0.27\%$
test_step_mdp_speed[True-True-False-True-True] 75.2520μs 42.8554μs 23.3343 KOps/s 23.6194 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[True-True-False-True-False] 54.9210μs 25.0986μs 39.8428 KOps/s 39.7823 KOps/s $\color{#35bf28}+0.15\%$
test_step_mdp_speed[True-True-False-False-True] 66.4910μs 24.0277μs 41.6186 KOps/s 40.2495 KOps/s $\color{#35bf28}+3.40\%$
test_step_mdp_speed[True-True-False-False-False] 36.6600μs 15.0592μs 66.4048 KOps/s 66.8317 KOps/s $\color{#d91a1a}-0.64\%$
test_step_mdp_speed[True-False-True-True-True] 86.5610μs 44.8483μs 22.2974 KOps/s 22.1408 KOps/s $\color{#35bf28}+0.71\%$
test_step_mdp_speed[True-False-True-True-False] 61.2510μs 27.0597μs 36.9553 KOps/s 36.9965 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[True-False-True-False-True] 62.0020μs 24.2077μs 41.3092 KOps/s 41.6616 KOps/s $\color{#d91a1a}-0.85\%$
test_step_mdp_speed[True-False-True-False-False] 48.5610μs 15.0274μs 66.5450 KOps/s 66.4927 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[True-False-False-True-True] 76.1310μs 47.0255μs 21.2651 KOps/s 21.4685 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[True-False-False-True-False] 54.5610μs 29.5353μs 33.8578 KOps/s 33.7006 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[True-False-False-False-True] 57.0010μs 26.0859μs 38.3348 KOps/s 38.5902 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-False-False-False-False] 40.2010μs 16.9985μs 58.8288 KOps/s 58.2640 KOps/s $\color{#35bf28}+0.97\%$
test_step_mdp_speed[False-True-True-True-True] 0.1012ms 43.6265μs 22.9219 KOps/s 22.2268 KOps/s $\color{#35bf28}+3.13\%$
test_step_mdp_speed[False-True-True-True-False] 56.0610μs 27.2347μs 36.7179 KOps/s 36.9414 KOps/s $\color{#d91a1a}-0.61\%$
test_step_mdp_speed[False-True-True-False-True] 59.3610μs 27.7431μs 36.0450 KOps/s 35.2088 KOps/s $\color{#35bf28}+2.38\%$
test_step_mdp_speed[False-True-True-False-False] 41.6310μs 16.6542μs 60.0450 KOps/s 60.2091 KOps/s $\color{#d91a1a}-0.27\%$
test_step_mdp_speed[False-True-False-True-True] 89.2520μs 47.4640μs 21.0686 KOps/s 21.3218 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[False-True-False-True-False] 76.2620μs 29.8871μs 33.4592 KOps/s 34.0690 KOps/s $\color{#d91a1a}-1.79\%$
test_step_mdp_speed[False-True-False-False-True] 3.2212ms 30.3110μs 32.9913 KOps/s 32.3637 KOps/s $\color{#35bf28}+1.94\%$
test_step_mdp_speed[False-True-False-False-False] 74.8510μs 18.8342μs 53.0948 KOps/s 52.5379 KOps/s $\color{#35bf28}+1.06\%$
test_step_mdp_speed[False-False-True-True-True] 93.3720μs 49.4556μs 20.2202 KOps/s 20.2664 KOps/s $\color{#d91a1a}-0.23\%$
test_step_mdp_speed[False-False-True-True-False] 78.0620μs 32.4636μs 30.8037 KOps/s 31.3797 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[False-False-True-False-True] 60.0810μs 29.9880μs 33.3467 KOps/s 32.6154 KOps/s $\color{#35bf28}+2.24\%$
test_step_mdp_speed[False-False-True-False-False] 54.0510μs 18.8143μs 53.1511 KOps/s 53.0403 KOps/s $\color{#35bf28}+0.21\%$
test_step_mdp_speed[False-False-False-True-True] 0.1039ms 51.0093μs 19.6043 KOps/s 19.3640 KOps/s $\color{#35bf28}+1.24\%$
test_step_mdp_speed[False-False-False-True-False] 67.3210μs 33.4825μs 29.8663 KOps/s 29.6043 KOps/s $\color{#35bf28}+0.89\%$
test_step_mdp_speed[False-False-False-False-True] 70.0510μs 31.3679μs 31.8797 KOps/s 31.2307 KOps/s $\color{#35bf28}+2.08\%$
test_step_mdp_speed[False-False-False-False-False] 51.5510μs 20.6999μs 48.3094 KOps/s 48.4886 KOps/s $\color{#d91a1a}-0.37\%$
test_values[generalized_advantage_estimate-True-True] 25.4114ms 25.0402ms 39.9358 Ops/s 39.4344 Ops/s $\color{#35bf28}+1.27\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1057s 3.0213ms 330.9820 Ops/s 332.1259 Ops/s $\color{#d91a1a}-0.34\%$
test_values[td0_return_estimate-False-False] 0.1105ms 83.5329μs 11.9713 KOps/s 11.9425 KOps/s $\color{#35bf28}+0.24\%$
test_values[td1_return_estimate-False-False] 56.7808ms 55.8219ms 17.9141 Ops/s 17.9134 Ops/s $+0.00\%$
test_values[vec_td1_return_estimate-False-False] 1.3353ms 1.0946ms 913.6130 Ops/s 902.6126 Ops/s $\color{#35bf28}+1.22\%$
test_values[td_lambda_return_estimate-True-False] 88.9259ms 88.3209ms 11.3224 Ops/s 11.1474 Ops/s $\color{#35bf28}+1.57\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2465ms 1.0892ms 918.1096 Ops/s 913.9841 Ops/s $\color{#35bf28}+0.45\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.3750ms 24.8189ms 40.2920 Ops/s 37.7593 Ops/s $\textbf{\color{#35bf28}+6.71\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0556ms 0.7682ms 1.3018 KOps/s 1.3025 KOps/s $\color{#d91a1a}-0.06\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8189ms 0.6812ms 1.4679 KOps/s 1.4668 KOps/s $\color{#35bf28}+0.08\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5507ms 1.4924ms 670.0596 Ops/s 668.5065 Ops/s $\color{#35bf28}+0.23\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7350ms 0.6950ms 1.4389 KOps/s 1.4358 KOps/s $\color{#35bf28}+0.22\%$
test_dqn_speed[False-None] 7.0303ms 1.4897ms 671.2603 Ops/s 670.5267 Ops/s $\color{#35bf28}+0.11\%$
test_dqn_speed[False-backward] 2.1525ms 2.1033ms 475.4437 Ops/s 471.3228 Ops/s $\color{#35bf28}+0.87\%$
test_dqn_speed[True-None] 0.6486ms 0.5355ms 1.8675 KOps/s 1.8343 KOps/s $\color{#35bf28}+1.81\%$
test_dqn_speed[True-backward] 1.3008ms 1.2240ms 817.0218 Ops/s 814.5832 Ops/s $\color{#35bf28}+0.30\%$
test_dqn_speed[reduce-overhead-None] 0.6381ms 0.5562ms 1.7978 KOps/s 1.7888 KOps/s $\color{#35bf28}+0.50\%$
test_dqn_speed[reduce-overhead-backward] 1.1315ms 1.0760ms 929.3882 Ops/s 1.0185 KOps/s $\textbf{\color{#d91a1a}-8.75\%}$
test_ddpg_speed[False-None] 3.1032ms 2.7930ms 358.0321 Ops/s 356.1783 Ops/s $\color{#35bf28}+0.52\%$
test_ddpg_speed[False-backward] 4.6683ms 4.2012ms 238.0287 Ops/s 243.3375 Ops/s $\color{#d91a1a}-2.18\%$
test_ddpg_speed[True-None] 1.1575ms 1.0821ms 924.1146 Ops/s 909.0319 Ops/s $\color{#35bf28}+1.66\%$
test_ddpg_speed[True-backward] 2.3763ms 2.3136ms 432.2184 Ops/s 451.7989 Ops/s $\color{#d91a1a}-4.33\%$
test_ddpg_speed[reduce-overhead-None] 1.3170ms 1.1064ms 903.8191 Ops/s 899.3446 Ops/s $\color{#35bf28}+0.50\%$
test_ddpg_speed[reduce-overhead-backward] 1.8565ms 1.8040ms 554.3365 Ops/s 581.6539 Ops/s $\color{#d91a1a}-4.70\%$
test_sac_speed[False-None] 8.5729ms 8.0778ms 123.7967 Ops/s 122.0061 Ops/s $\color{#35bf28}+1.47\%$
test_sac_speed[False-backward] 11.7629ms 11.3337ms 88.2327 Ops/s 90.1381 Ops/s $\color{#d91a1a}-2.11\%$
test_sac_speed[True-None] 1.6583ms 1.5515ms 644.5342 Ops/s 635.7478 Ops/s $\color{#35bf28}+1.38\%$
test_sac_speed[True-backward] 3.4705ms 3.3993ms 294.1776 Ops/s 304.7799 Ops/s $\color{#d91a1a}-3.48\%$
test_sac_speed[reduce-overhead-None] 22.5285ms 12.5527ms 79.6640 Ops/s 80.9607 Ops/s $\color{#d91a1a}-1.60\%$
test_sac_speed[reduce-overhead-backward] 1.3958ms 1.3496ms 740.9355 Ops/s 730.9318 Ops/s $\color{#35bf28}+1.37\%$
test_redq_speed[False-None] 8.3456ms 7.5513ms 132.4281 Ops/s 130.2838 Ops/s $\color{#35bf28}+1.65\%$
test_redq_speed[False-backward] 12.2244ms 11.4746ms 87.1487 Ops/s 86.4240 Ops/s $\color{#35bf28}+0.84\%$
test_redq_speed[True-None] 2.2984ms 2.0458ms 488.8048 Ops/s 497.3872 Ops/s $\color{#d91a1a}-1.73\%$
test_redq_speed[True-backward] 4.2047ms 3.7578ms 266.1131 Ops/s 255.3301 Ops/s $\color{#35bf28}+4.22\%$
test_redq_speed[reduce-overhead-None] 2.1911ms 2.0134ms 496.6640 Ops/s 493.4043 Ops/s $\color{#35bf28}+0.66\%$
test_redq_speed[reduce-overhead-backward] 4.1859ms 3.7427ms 267.1903 Ops/s 252.2943 Ops/s $\textbf{\color{#35bf28}+5.90\%}$
test_redq_deprec_speed[False-None] 9.7186ms 9.0866ms 110.0523 Ops/s 109.6844 Ops/s $\color{#35bf28}+0.34\%$
test_redq_deprec_speed[False-backward] 12.5657ms 12.1416ms 82.3617 Ops/s 79.5845 Ops/s $\color{#35bf28}+3.49\%$
test_redq_deprec_speed[True-None] 2.5661ms 2.3501ms 425.5205 Ops/s 425.0919 Ops/s $\color{#35bf28}+0.10\%$
test_redq_deprec_speed[True-backward] 4.5935ms 4.0622ms 246.1710 Ops/s 245.4539 Ops/s $\color{#35bf28}+0.29\%$
test_redq_deprec_speed[reduce-overhead-None] 2.4405ms 2.3384ms 427.6414 Ops/s 420.7381 Ops/s $\color{#35bf28}+1.64\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.5188ms 4.0406ms 247.4886 Ops/s 245.2198 Ops/s $\color{#35bf28}+0.93\%$
test_td3_speed[False-None] 8.0880ms 7.9313ms 126.0822 Ops/s 126.0050 Ops/s $\color{#35bf28}+0.06\%$
test_td3_speed[False-backward] 11.0330ms 10.3595ms 96.5301 Ops/s 97.4283 Ops/s $\color{#d91a1a}-0.92\%$
test_td3_speed[True-None] 1.6605ms 1.5869ms 630.1579 Ops/s 630.1900 Ops/s $-0.01\%$
test_td3_speed[True-backward] 3.5654ms 3.1204ms 320.4752 Ops/s 299.1589 Ops/s $\textbf{\color{#35bf28}+7.13\%}$
test_td3_speed[reduce-overhead-None] 50.7330ms 25.9579ms 38.5239 Ops/s 36.9784 Ops/s $\color{#35bf28}+4.18\%$
test_td3_speed[reduce-overhead-backward] 1.3802ms 1.2963ms 771.4508 Ops/s 684.7371 Ops/s $\textbf{\color{#35bf28}+12.66\%}$
test_cql_speed[False-None] 16.5067ms 16.1779ms 61.8126 Ops/s 60.9727 Ops/s $\color{#35bf28}+1.38\%$
test_cql_speed[False-backward] 22.1941ms 21.5430ms 46.4187 Ops/s 45.4814 Ops/s $\color{#35bf28}+2.06\%$
test_cql_speed[True-None] 3.1016ms 2.9318ms 341.0882 Ops/s 337.8787 Ops/s $\color{#35bf28}+0.95\%$
test_cql_speed[True-backward] 5.7246ms 5.3045ms 188.5196 Ops/s 189.9027 Ops/s $\color{#d91a1a}-0.73\%$
test_cql_speed[reduce-overhead-None] 22.0976ms 12.9914ms 76.9738 Ops/s 75.3841 Ops/s $\color{#35bf28}+2.11\%$
test_cql_speed[reduce-overhead-backward] 1.7523ms 1.6871ms 592.7270 Ops/s 646.5889 Ops/s $\textbf{\color{#d91a1a}-8.33\%}$
test_a2c_speed[False-None] 3.5058ms 3.2445ms 308.2109 Ops/s 310.4319 Ops/s $\color{#d91a1a}-0.72\%$
test_a2c_speed[False-backward] 7.1078ms 6.4456ms 155.1456 Ops/s 160.0172 Ops/s $\color{#d91a1a}-3.04\%$
test_a2c_speed[True-None] 1.0789ms 0.9988ms 1.0012 KOps/s 991.1893 Ops/s $\color{#35bf28}+1.01\%$
test_a2c_speed[True-backward] 2.8480ms 2.7975ms 357.4562 Ops/s 376.6929 Ops/s $\textbf{\color{#d91a1a}-5.11\%}$
test_a2c_speed[reduce-overhead-None] 0.3951s 12.3757ms 80.8032 Ops/s 85.2213 Ops/s $\textbf{\color{#d91a1a}-5.18\%}$
test_a2c_speed[reduce-overhead-backward] 1.2381ms 1.1694ms 855.1355 Ops/s 996.4269 Ops/s $\textbf{\color{#d91a1a}-14.18\%}$
test_ppo_speed[False-None] 3.7490ms 3.6487ms 274.0678 Ops/s 268.3267 Ops/s $\color{#35bf28}+2.14\%$
test_ppo_speed[False-backward] 7.5483ms 7.1381ms 140.0924 Ops/s 144.7341 Ops/s $\color{#d91a1a}-3.21\%$
test_ppo_speed[True-None] 1.0104ms 0.9433ms 1.0601 KOps/s 1.0369 KOps/s $\color{#35bf28}+2.23\%$
test_ppo_speed[True-backward] 3.1588ms 2.7725ms 360.6794 Ops/s 361.2452 Ops/s $\color{#d91a1a}-0.16\%$
test_ppo_speed[reduce-overhead-None] 0.5600ms 0.4985ms 2.0060 KOps/s 1.8622 KOps/s $\textbf{\color{#35bf28}+7.72\%}$
test_ppo_speed[reduce-overhead-backward] 1.1854ms 1.1444ms 873.8314 Ops/s 856.9570 Ops/s $\color{#35bf28}+1.97\%$
test_reinforce_speed[False-None] 2.3511ms 2.2235ms 449.7474 Ops/s 445.6212 Ops/s $\color{#35bf28}+0.93\%$
test_reinforce_speed[False-backward] 3.8495ms 3.4050ms 293.6900 Ops/s 297.5099 Ops/s $\color{#d91a1a}-1.28\%$
test_reinforce_speed[True-None] 0.9085ms 0.8329ms 1.2006 KOps/s 1.1869 KOps/s $\color{#35bf28}+1.15\%$
test_reinforce_speed[True-backward] 2.8512ms 2.5877ms 386.4509 Ops/s 383.3093 Ops/s $\color{#35bf28}+0.82\%$
test_reinforce_speed[reduce-overhead-None] 22.9237ms 11.9917ms 83.3911 Ops/s 87.0999 Ops/s $\color{#d91a1a}-4.26\%$
test_reinforce_speed[reduce-overhead-backward] 1.2519ms 1.2162ms 822.1999 Ops/s 831.9848 Ops/s $\color{#d91a1a}-1.18\%$
test_iql_speed[False-None] 9.6618ms 9.1182ms 109.6713 Ops/s 108.3653 Ops/s $\color{#35bf28}+1.21\%$
test_iql_speed[False-backward] 13.7388ms 13.2300ms 75.5857 Ops/s 75.4504 Ops/s $\color{#35bf28}+0.18\%$
test_iql_speed[True-None] 1.9703ms 1.7609ms 567.8868 Ops/s 565.9827 Ops/s $\color{#35bf28}+0.34\%$
test_iql_speed[True-backward] 4.6038ms 4.4470ms 224.8720 Ops/s 229.5406 Ops/s $\color{#d91a1a}-2.03\%$
test_iql_speed[reduce-overhead-None] 20.3226ms 11.6526ms 85.8176 Ops/s 86.2356 Ops/s $\color{#d91a1a}-0.48\%$
test_iql_speed[reduce-overhead-backward] 1.6723ms 1.6179ms 618.0895 Ops/s 687.1175 Ops/s $\textbf{\color{#d91a1a}-10.05\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9858ms 6.4593ms 154.8145 Ops/s 152.0079 Ops/s $\color{#35bf28}+1.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.4939ms 0.2742ms 3.6470 KOps/s 3.0911 KOps/s $\textbf{\color{#35bf28}+17.99\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5429ms 0.3487ms 2.8679 KOps/s 3.5048 KOps/s $\textbf{\color{#d91a1a}-18.17\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.6306ms 6.2824ms 159.1736 Ops/s 158.0464 Ops/s $\color{#35bf28}+0.71\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0243ms 0.2914ms 3.4313 KOps/s 2.9116 KOps/s $\textbf{\color{#35bf28}+17.85\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6404ms 0.2821ms 3.5446 KOps/s 3.1075 KOps/s $\textbf{\color{#35bf28}+14.07\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6513ms 1.4466ms 691.2670 Ops/s 685.3556 Ops/s $\color{#35bf28}+0.86\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.7071ms 1.3983ms 715.1410 Ops/s 714.6642 Ops/s $\color{#35bf28}+0.07\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4947ms 6.3543ms 157.3748 Ops/s 155.0738 Ops/s $\color{#35bf28}+1.48\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.1644ms 0.4117ms 2.4287 KOps/s 2.1362 KOps/s $\textbf{\color{#35bf28}+13.69\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6264ms 0.3861ms 2.5903 KOps/s 1.9697 KOps/s $\textbf{\color{#35bf28}+31.51\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.4137ms 6.2592ms 159.7642 Ops/s 159.3150 Ops/s $\color{#35bf28}+0.28\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.1048ms 0.3045ms 3.2838 KOps/s 3.1338 KOps/s $\color{#35bf28}+4.79\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4627ms 0.2915ms 3.4302 KOps/s 3.4847 KOps/s $\color{#d91a1a}-1.56\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 8.7391ms 6.2467ms 160.0838 Ops/s 159.3498 Ops/s $\color{#35bf28}+0.46\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.5342ms 0.3016ms 3.3157 KOps/s 2.9331 KOps/s $\textbf{\color{#35bf28}+13.05\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4323ms 0.2379ms 4.2032 KOps/s 3.2231 KOps/s $\textbf{\color{#35bf28}+30.41\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5511ms 6.3982ms 156.2951 Ops/s 154.8571 Ops/s $\color{#35bf28}+0.93\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9460ms 0.4166ms 2.4007 KOps/s 2.3846 KOps/s $\color{#35bf28}+0.67\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.5849ms 0.3848ms 2.5991 KOps/s 2.0294 KOps/s $\textbf{\color{#35bf28}+28.07\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.2221ms 5.3760ms 186.0110 Ops/s 188.2188 Ops/s $\color{#d91a1a}-1.17\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 11.3993ms 2.1131ms 473.2460 Ops/s 445.4528 Ops/s $\textbf{\color{#35bf28}+6.24\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.4159ms 1.1399ms 877.2993 Ops/s 817.2484 Ops/s $\textbf{\color{#35bf28}+7.35\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4960s 15.2617ms 65.5233 Ops/s 187.9750 Ops/s $\textbf{\color{#d91a1a}-65.14\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 3.7092ms 1.5788ms 633.3926 Ops/s 437.2899 Ops/s $\textbf{\color{#35bf28}+44.85\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 12.2913ms 1.3750ms 727.2763 Ops/s 826.1481 Ops/s $\textbf{\color{#d91a1a}-11.97\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 8.7481ms 5.6063ms 178.3695 Ops/s 33.1736 Ops/s $\textbf{\color{#35bf28}+437.68\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.9012ms 2.2886ms 436.9507 Ops/s 464.1463 Ops/s $\textbf{\color{#d91a1a}-5.86\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 8.1651ms 1.5189ms 658.3731 Ops/s 758.7082 Ops/s $\textbf{\color{#d91a1a}-13.22\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.8949ms 13.4613ms 74.2868 Ops/s 74.8057 Ops/s $\color{#d91a1a}-0.69\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 19.7334ms 16.9701ms 58.9272 Ops/s 57.6653 Ops/s $\color{#35bf28}+2.19\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.3454ms 17.4250ms 57.3886 Ops/s 55.1088 Ops/s $\color{#35bf28}+4.14\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 17.8910ms 17.3860ms 57.5174 Ops/s 57.4141 Ops/s $\color{#35bf28}+0.18\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 17.7839ms 17.4427ms 57.3307 Ops/s 54.1542 Ops/s $\textbf{\color{#35bf28}+5.87\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.3163ms 18.5109ms 54.0223 Ops/s 54.1012 Ops/s $\color{#d91a1a}-0.15\%$

@vmoens vmoens added bug Something isn't working enhancement New feature or request labels Nov 11, 2024
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