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 MARL PPO tutorial action_spec call #2628

Merged
merged 1 commit into from
Dec 3, 2024
Merged

[BugFix] Fix MARL PPO tutorial action_spec call #2628

merged 1 commit into from
Dec 3, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Dec 3, 2024 •
edited
Loading

@vmoens
Update
b4dd118 
[ghstack-poisoned]
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Dec 3, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2628

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

❌ 11 New Failures, 5 Unrelated Failures

As of commit b4dd118 with merge base aed03fd (image):

NEW FAILURES - The following jobs have failed:

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.

@vmoens vmoens mentioned this pull request Dec 3, 2024
Merged
@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 Dec 3, 2024
@vmoens vmoens merged commit b4dd118 into gh/vmoens/48/base Dec 3, 2024
35 of 51 checks passed
vmoens added a commit that referenced this pull request Dec 3, 2024
@vmoens
[BugFix] Fix MARL PPO tutorial action_spec call
1ca134c 
ghstack-source-id: 1d9058c45b28c0f0279e4243a2a0f96c622a51d8
Pull Request resolved: #2628
@vmoens vmoens deleted the gh/vmoens/48/head branch December 3, 2024 15:06
@github-actions GitHub Actions
Copy link

github-actions bot commented Dec 3, 2024

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}37$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4298s 0.4283s 2.3350 Ops/s 2.2069 Ops/s $\textbf{\color{#35bf28}+5.80\%}$
test_transformed 0.6168s 0.6147s 1.6269 Ops/s 1.6390 Ops/s $\color{#d91a1a}-0.74\%$
test_serial 1.3554s 1.3543s 0.7384 Ops/s 0.7288 Ops/s $\color{#35bf28}+1.32\%$
test_parallel 1.4010s 1.3081s 0.7645 Ops/s 0.7585 Ops/s $\color{#35bf28}+0.79\%$
test_step_mdp_speed[True-True-True-True-True] 0.2430ms 30.3509μs 32.9480 KOps/s 33.0757 KOps/s $\color{#d91a1a}-0.39\%$
test_step_mdp_speed[True-True-True-True-False] 55.8550μs 17.8619μs 55.9852 KOps/s 56.8090 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[True-True-True-False-True] 71.1730μs 17.2331μs 58.0278 KOps/s 59.1227 KOps/s $\color{#d91a1a}-1.85\%$
test_step_mdp_speed[True-True-True-False-False] 34.3240μs 10.0735μs 99.2701 KOps/s 101.4218 KOps/s $\color{#d91a1a}-2.12\%$
test_step_mdp_speed[True-True-False-True-True] 78.6290μs 32.5332μs 30.7379 KOps/s 31.0064 KOps/s $\color{#d91a1a}-0.87\%$
test_step_mdp_speed[True-True-False-True-False] 62.5980μs 19.7474μs 50.6396 KOps/s 51.1598 KOps/s $\color{#d91a1a}-1.02\%$
test_step_mdp_speed[True-True-False-False-True] 68.5700μs 19.1605μs 52.1906 KOps/s 53.0331 KOps/s $\color{#d91a1a}-1.59\%$
test_step_mdp_speed[True-True-False-False-False] 36.2490μs 11.9304μs 83.8194 KOps/s 84.7031 KOps/s $\color{#d91a1a}-1.04\%$
test_step_mdp_speed[True-False-True-True-True] 87.2850μs 34.5207μs 28.9681 KOps/s 29.5508 KOps/s $\color{#d91a1a}-1.97\%$
test_step_mdp_speed[True-False-True-True-False] 73.0680μs 21.7929μs 45.8866 KOps/s 47.2085 KOps/s $\color{#d91a1a}-2.80\%$
test_step_mdp_speed[True-False-True-False-True] 49.1430μs 19.2699μs 51.8943 KOps/s 53.3684 KOps/s $\color{#d91a1a}-2.76\%$
test_step_mdp_speed[True-False-True-False-False] 55.9260μs 12.0001μs 83.3323 KOps/s 85.0453 KOps/s $\color{#d91a1a}-2.01\%$
test_step_mdp_speed[True-False-False-True-True] 78.6590μs 36.1087μs 27.6941 KOps/s 28.1495 KOps/s $\color{#d91a1a}-1.62\%$
test_step_mdp_speed[True-False-False-True-False] 71.3650μs 23.2686μs 42.9764 KOps/s 42.6813 KOps/s $\color{#35bf28}+0.69\%$
test_step_mdp_speed[True-False-False-False-True] 70.7730μs 20.7330μs 48.2322 KOps/s 49.0896 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[True-False-False-False-False] 42.4890μs 13.6504μs 73.2578 KOps/s 74.3352 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[False-True-True-True-True] 86.4310μs 34.4901μs 28.9939 KOps/s 29.5533 KOps/s $\color{#d91a1a}-1.89\%$
test_step_mdp_speed[False-True-True-True-False] 70.0130μs 21.5974μs 46.3018 KOps/s 46.8402 KOps/s $\color{#d91a1a}-1.15\%$
test_step_mdp_speed[False-True-True-False-True] 61.1150μs 21.6708μs 46.1450 KOps/s 47.5550 KOps/s $\color{#d91a1a}-2.97\%$
test_step_mdp_speed[False-True-True-False-False] 47.6890μs 13.5686μs 73.6993 KOps/s 76.7792 KOps/s $\color{#d91a1a}-4.01\%$
test_step_mdp_speed[False-True-False-True-True] 79.3590μs 36.3200μs 27.5330 KOps/s 28.3687 KOps/s $\color{#d91a1a}-2.95\%$
test_step_mdp_speed[False-True-False-True-False] 75.8720μs 23.6530μs 42.2780 KOps/s 43.5349 KOps/s $\color{#d91a1a}-2.89\%$
test_step_mdp_speed[False-True-False-False-True] 3.1267ms 23.7842μs 42.0447 KOps/s 43.5450 KOps/s $\color{#d91a1a}-3.45\%$
test_step_mdp_speed[False-True-False-False-False] 40.8460μs 15.2484μs 65.5804 KOps/s 67.2816 KOps/s $\color{#d91a1a}-2.53\%$
test_step_mdp_speed[False-False-True-True-True] 84.1470μs 38.3895μs 26.0488 KOps/s 26.7406 KOps/s $\color{#d91a1a}-2.59\%$
test_step_mdp_speed[False-False-True-True-False] 66.2840μs 25.1586μs 39.7478 KOps/s 39.8561 KOps/s $\color{#d91a1a}-0.27\%$
test_step_mdp_speed[False-False-True-False-True] 67.8970μs 24.0900μs 41.5110 KOps/s 43.9434 KOps/s $\textbf{\color{#d91a1a}-5.54\%}$
test_step_mdp_speed[False-False-True-False-False] 45.1440μs 15.2969μs 65.3726 KOps/s 66.8259 KOps/s $\color{#d91a1a}-2.17\%$
test_step_mdp_speed[False-False-False-True-True] 94.9880μs 39.1986μs 25.5111 KOps/s 25.6814 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[False-False-False-True-False] 87.5040μs 27.0807μs 36.9267 KOps/s 37.8105 KOps/s $\color{#d91a1a}-2.34\%$
test_step_mdp_speed[False-False-False-False-True] 63.2500μs 25.3179μs 39.4978 KOps/s 41.2664 KOps/s $\color{#d91a1a}-4.29\%$
test_step_mdp_speed[False-False-False-False-False] 80.6280μs 16.3943μs 60.9968 KOps/s 61.4112 KOps/s $\color{#d91a1a}-0.67\%$
test_values[generalized_advantage_estimate-True-True] 12.6671ms 10.0147ms 99.8532 Ops/s 102.1668 Ops/s $\color{#d91a1a}-2.26\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.6890ms 33.3993ms 29.9407 Ops/s 29.7423 Ops/s $\color{#35bf28}+0.67\%$
test_values[td0_return_estimate-False-False] 0.2304ms 0.1734ms 5.7670 KOps/s 5.6423 KOps/s $\color{#35bf28}+2.21\%$
test_values[td1_return_estimate-False-False] 25.7166ms 24.8696ms 40.2098 Ops/s 42.5869 Ops/s $\textbf{\color{#d91a1a}-5.58\%}$
test_values[vec_td1_return_estimate-False-False] 36.1260ms 33.5288ms 29.8251 Ops/s 29.8366 Ops/s $\color{#d91a1a}-0.04\%$
test_values[td_lambda_return_estimate-True-False] 36.4009ms 35.3606ms 28.2801 Ops/s 29.6539 Ops/s $\color{#d91a1a}-4.63\%$
test_values[vec_td_lambda_return_estimate-True-False] 35.9818ms 33.4946ms 29.8556 Ops/s 28.5177 Ops/s $\color{#35bf28}+4.69\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 9.2020ms 8.4272ms 118.6638 Ops/s 122.9334 Ops/s $\color{#d91a1a}-3.47\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 3.1008ms 2.1258ms 470.4188 Ops/s 550.0055 Ops/s $\textbf{\color{#d91a1a}-14.47\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5677ms 0.3613ms 2.7678 KOps/s 2.7444 KOps/s $\color{#35bf28}+0.85\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 43.7847ms 42.4316ms 23.5673 Ops/s 23.8420 Ops/s $\color{#d91a1a}-1.15\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.9659ms 3.0517ms 327.6878 Ops/s 325.4602 Ops/s $\color{#35bf28}+0.68\%$
test_dqn_speed[False-None] 1.8877ms 1.3996ms 714.5138 Ops/s 708.9759 Ops/s $\color{#35bf28}+0.78\%$
test_dqn_speed[False-backward] 1.9107ms 1.8657ms 536.0009 Ops/s 527.8505 Ops/s $\color{#35bf28}+1.54\%$
test_dqn_speed[True-None] 0.7852ms 0.4713ms 2.1217 KOps/s 2.0679 KOps/s $\color{#35bf28}+2.60\%$
test_dqn_speed[True-backward] 1.0003ms 0.8982ms 1.1133 KOps/s 1.1005 KOps/s $\color{#35bf28}+1.16\%$
test_dqn_speed[reduce-overhead-None] 0.7635ms 0.4705ms 2.1253 KOps/s 2.1361 KOps/s $\color{#d91a1a}-0.50\%$
test_dqn_speed[reduce-overhead-backward] 0.9356ms 0.8863ms 1.1283 KOps/s 1.1058 KOps/s $\color{#35bf28}+2.03\%$
test_ddpg_speed[False-None] 4.2286ms 2.9092ms 343.7377 Ops/s 347.5846 Ops/s $\color{#d91a1a}-1.11\%$
test_ddpg_speed[False-backward] 4.1692ms 4.0361ms 247.7657 Ops/s 249.8949 Ops/s $\color{#d91a1a}-0.85\%$
test_ddpg_speed[True-None] 1.7052ms 1.0232ms 977.3206 Ops/s 985.6385 Ops/s $\color{#d91a1a}-0.84\%$
test_ddpg_speed[True-backward] 2.0214ms 1.9199ms 520.8665 Ops/s 498.0034 Ops/s $\color{#35bf28}+4.59\%$
test_ddpg_speed[reduce-overhead-None] 1.3351ms 1.0110ms 989.1263 Ops/s 979.4642 Ops/s $\color{#35bf28}+0.99\%$
test_ddpg_speed[reduce-overhead-backward] 1.9811ms 1.9050ms 524.9224 Ops/s 513.2043 Ops/s $\color{#35bf28}+2.28\%$
test_sac_speed[False-None] 8.5164ms 8.0272ms 124.5760 Ops/s 117.5140 Ops/s $\textbf{\color{#35bf28}+6.01\%}$
test_sac_speed[False-backward] 13.0109ms 10.8805ms 91.9072 Ops/s 79.8911 Ops/s $\textbf{\color{#35bf28}+15.04\%}$
test_sac_speed[True-None] 2.2235ms 1.8389ms 543.7919 Ops/s 448.5761 Ops/s $\textbf{\color{#35bf28}+21.23\%}$
test_sac_speed[True-backward] 3.5748ms 3.5191ms 284.1666 Ops/s 280.2628 Ops/s $\color{#35bf28}+1.39\%$
test_sac_speed[reduce-overhead-None] 2.7019ms 1.8471ms 541.3914 Ops/s 524.4025 Ops/s $\color{#35bf28}+3.24\%$
test_sac_speed[reduce-overhead-backward] 3.9105ms 3.6457ms 274.2924 Ops/s 278.2916 Ops/s $\color{#d91a1a}-1.44\%$
test_redq_speed[False-None] 13.5185ms 12.7243ms 78.5900 Ops/s 71.9828 Ops/s $\textbf{\color{#35bf28}+9.18\%}$
test_redq_speed[False-backward] 23.7271ms 22.1439ms 45.1591 Ops/s 45.1436 Ops/s $\color{#35bf28}+0.03\%$
test_redq_speed[True-None] 5.6015ms 4.5435ms 220.0960 Ops/s 209.9721 Ops/s $\color{#35bf28}+4.82\%$
test_redq_speed[True-backward] 13.0094ms 12.0369ms 83.0780 Ops/s 76.5934 Ops/s $\textbf{\color{#35bf28}+8.47\%}$
test_redq_speed[reduce-overhead-None] 5.3476ms 4.5436ms 220.0891 Ops/s 191.8658 Ops/s $\textbf{\color{#35bf28}+14.71\%}$
test_redq_speed[reduce-overhead-backward] 13.1269ms 12.0208ms 83.1894 Ops/s 76.5432 Ops/s $\textbf{\color{#35bf28}+8.68\%}$
test_redq_deprec_speed[False-None] 14.9873ms 12.8862ms 77.6024 Ops/s 72.1490 Ops/s $\textbf{\color{#35bf28}+7.56\%}$
test_redq_deprec_speed[False-backward] 21.6920ms 18.5918ms 53.7871 Ops/s 50.5646 Ops/s $\textbf{\color{#35bf28}+6.37\%}$
test_redq_deprec_speed[True-None] 4.0719ms 3.5646ms 280.5384 Ops/s 250.3562 Ops/s $\textbf{\color{#35bf28}+12.06\%}$
test_redq_deprec_speed[True-backward] 9.8249ms 8.1209ms 123.1390 Ops/s 122.5113 Ops/s $\color{#35bf28}+0.51\%$
test_redq_deprec_speed[reduce-overhead-None] 4.2107ms 3.5632ms 280.6491 Ops/s 249.5482 Ops/s $\textbf{\color{#35bf28}+12.46\%}$
test_redq_deprec_speed[reduce-overhead-backward] 8.4273ms 7.9792ms 125.3258 Ops/s 123.7658 Ops/s $\color{#35bf28}+1.26\%$
test_td3_speed[False-None] 8.4785ms 8.0098ms 124.8468 Ops/s 121.2731 Ops/s $\color{#35bf28}+2.95\%$
test_td3_speed[False-backward] 12.0821ms 10.4656ms 95.5514 Ops/s 95.3739 Ops/s $\color{#35bf28}+0.19\%$
test_td3_speed[True-None] 1.8171ms 1.7031ms 587.1498 Ops/s 540.8831 Ops/s $\textbf{\color{#35bf28}+8.55\%}$
test_td3_speed[True-backward] 3.8014ms 3.3546ms 298.0981 Ops/s 242.9358 Ops/s $\textbf{\color{#35bf28}+22.71\%}$
test_td3_speed[reduce-overhead-None] 1.8724ms 1.7064ms 586.0192 Ops/s 489.9115 Ops/s $\textbf{\color{#35bf28}+19.62\%}$
test_td3_speed[reduce-overhead-backward] 3.4580ms 3.3051ms 302.5587 Ops/s 230.6654 Ops/s $\textbf{\color{#35bf28}+31.17\%}$
test_cql_speed[False-None] 39.1445ms 35.5993ms 28.0904 Ops/s 24.9632 Ops/s $\textbf{\color{#35bf28}+12.53\%}$
test_cql_speed[False-backward] 47.8687ms 45.7227ms 21.8710 Ops/s 19.3482 Ops/s $\textbf{\color{#35bf28}+13.04\%}$
test_cql_speed[True-None] 17.1569ms 15.5751ms 64.2052 Ops/s 61.2352 Ops/s $\color{#35bf28}+4.85\%$
test_cql_speed[True-backward] 23.2174ms 22.0703ms 45.3099 Ops/s 40.4312 Ops/s $\textbf{\color{#35bf28}+12.07\%}$
test_cql_speed[reduce-overhead-None] 16.9175ms 15.4747ms 64.6214 Ops/s 62.7714 Ops/s $\color{#35bf28}+2.95\%$
test_cql_speed[reduce-overhead-backward] 23.7544ms 22.2523ms 44.9392 Ops/s 42.0291 Ops/s $\textbf{\color{#35bf28}+6.92\%}$
test_a2c_speed[False-None] 8.1235ms 7.1834ms 139.2100 Ops/s 136.2482 Ops/s $\color{#35bf28}+2.17\%$
test_a2c_speed[False-backward] 15.5077ms 14.2428ms 70.2111 Ops/s 68.4478 Ops/s $\color{#35bf28}+2.58\%$
test_a2c_speed[True-None] 4.7519ms 4.2137ms 237.3188 Ops/s 203.4415 Ops/s $\textbf{\color{#35bf28}+16.65\%}$
test_a2c_speed[True-backward] 11.4841ms 10.7461ms 93.0570 Ops/s 81.1545 Ops/s $\textbf{\color{#35bf28}+14.67\%}$
test_a2c_speed[reduce-overhead-None] 4.7261ms 4.1710ms 239.7533 Ops/s 198.3708 Ops/s $\textbf{\color{#35bf28}+20.86\%}$
test_a2c_speed[reduce-overhead-backward] 11.6487ms 10.6869ms 93.5724 Ops/s 79.1048 Ops/s $\textbf{\color{#35bf28}+18.29\%}$
test_ppo_speed[False-None] 9.3003ms 7.5011ms 133.3141 Ops/s 111.8554 Ops/s $\textbf{\color{#35bf28}+19.18\%}$
test_ppo_speed[False-backward] 15.0774ms 14.5889ms 68.5453 Ops/s 61.1656 Ops/s $\textbf{\color{#35bf28}+12.06\%}$
test_ppo_speed[True-None] 5.9783ms 3.6741ms 272.1743 Ops/s 267.3045 Ops/s $\color{#35bf28}+1.82\%$
test_ppo_speed[True-backward] 11.0791ms 9.6070ms 104.0907 Ops/s 97.9745 Ops/s $\textbf{\color{#35bf28}+6.24\%}$
test_ppo_speed[reduce-overhead-None] 4.0160ms 3.6690ms 272.5512 Ops/s 270.4869 Ops/s $\color{#35bf28}+0.76\%$
test_ppo_speed[reduce-overhead-backward] 10.2039ms 9.5275ms 104.9590 Ops/s 95.7199 Ops/s $\textbf{\color{#35bf28}+9.65\%}$
test_reinforce_speed[False-None] 7.5454ms 6.5044ms 153.7422 Ops/s 142.4203 Ops/s $\textbf{\color{#35bf28}+7.95\%}$
test_reinforce_speed[False-backward] 10.7238ms 9.8609ms 101.4111 Ops/s 94.3785 Ops/s $\textbf{\color{#35bf28}+7.45\%}$
test_reinforce_speed[True-None] 3.1871ms 2.6224ms 381.3357 Ops/s 345.2327 Ops/s $\textbf{\color{#35bf28}+10.46\%}$
test_reinforce_speed[True-backward] 9.1072ms 8.5461ms 117.0122 Ops/s 115.0764 Ops/s $\color{#35bf28}+1.68\%$
test_reinforce_speed[reduce-overhead-None] 3.1937ms 2.6260ms 380.8005 Ops/s 376.3323 Ops/s $\color{#35bf28}+1.19\%$
test_reinforce_speed[reduce-overhead-backward] 8.9251ms 8.5249ms 117.3032 Ops/s 114.1407 Ops/s $\color{#35bf28}+2.77\%$
test_iql_speed[False-None] 33.4027ms 31.7359ms 31.5100 Ops/s 31.1379 Ops/s $\color{#35bf28}+1.20\%$
test_iql_speed[False-backward] 46.0593ms 44.4913ms 22.4763 Ops/s 21.8845 Ops/s $\color{#35bf28}+2.70\%$
test_iql_speed[True-None] 11.1222ms 10.3983ms 96.1694 Ops/s 89.0621 Ops/s $\textbf{\color{#35bf28}+7.98\%}$
test_iql_speed[True-backward] 22.5178ms 21.2473ms 47.0649 Ops/s 45.3836 Ops/s $\color{#35bf28}+3.70\%$
test_iql_speed[reduce-overhead-None] 11.7357ms 10.4058ms 96.1005 Ops/s 88.5188 Ops/s $\textbf{\color{#35bf28}+8.57\%}$
test_iql_speed[reduce-overhead-backward] 22.4592ms 21.2643ms 47.0272 Ops/s 45.2694 Ops/s $\color{#35bf28}+3.88\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.1433ms 4.8645ms 205.5722 Ops/s 197.2528 Ops/s $\color{#35bf28}+4.22\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0356ms 0.5091ms 1.9642 KOps/s 1.9219 KOps/s $\color{#35bf28}+2.20\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6957ms 0.4880ms 2.0492 KOps/s 2.0405 KOps/s $\color{#35bf28}+0.43\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4257ms 4.6818ms 213.5944 Ops/s 209.2444 Ops/s $\color{#35bf28}+2.08\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8872ms 0.4931ms 2.0280 KOps/s 2.0223 KOps/s $\color{#35bf28}+0.28\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6656ms 0.4753ms 2.1039 KOps/s 2.0896 KOps/s $\color{#35bf28}+0.69\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.2028ms 1.6294ms 613.7072 Ops/s 610.1672 Ops/s $\color{#35bf28}+0.58\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.0660ms 1.5821ms 632.0631 Ops/s 618.5246 Ops/s $\color{#35bf28}+2.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2654ms 4.8380ms 206.6973 Ops/s 202.2476 Ops/s $\color{#35bf28}+2.20\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.3319ms 0.6387ms 1.5657 KOps/s 1.5455 KOps/s $\color{#35bf28}+1.31\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9324ms 0.6154ms 1.6249 KOps/s 1.6154 KOps/s $\color{#35bf28}+0.59\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.4435ms 4.7507ms 210.4954 Ops/s 210.3979 Ops/s $\color{#35bf28}+0.05\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.9610ms 0.5153ms 1.9407 KOps/s 1.9389 KOps/s $\color{#35bf28}+0.09\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6774ms 0.4881ms 2.0486 KOps/s 1.9119 KOps/s $\textbf{\color{#35bf28}+7.15\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.3343ms 4.7290ms 211.4613 Ops/s 211.4003 Ops/s $\color{#35bf28}+0.03\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6772ms 0.4929ms 2.0287 KOps/s 2.0055 KOps/s $\color{#35bf28}+1.16\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 7.4141ms 0.4842ms 2.0654 KOps/s 2.1080 KOps/s $\color{#d91a1a}-2.02\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.8416ms 4.8102ms 207.8936 Ops/s 204.7754 Ops/s $\color{#35bf28}+1.52\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8400ms 0.6434ms 1.5543 KOps/s 1.5613 KOps/s $\color{#d91a1a}-0.45\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 8.3996ms 0.6366ms 1.5709 KOps/s 1.5993 KOps/s $\color{#d91a1a}-1.78\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.5449ms 4.2075ms 237.6721 Ops/s 250.1717 Ops/s $\color{#d91a1a}-5.00\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.1991ms 2.1056ms 474.9266 Ops/s 438.2739 Ops/s $\textbf{\color{#35bf28}+8.36\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.2980ms 1.3040ms 766.8877 Ops/s 834.1092 Ops/s $\textbf{\color{#d91a1a}-8.06\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 6.0105ms 4.3015ms 232.4772 Ops/s 39.3946 Ops/s $\textbf{\color{#35bf28}+490.12\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.3972s 10.1409ms 98.6110 Ops/s 493.8443 Ops/s $\textbf{\color{#d91a1a}-80.03\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.6406ms 1.2785ms 782.1519 Ops/s 728.3429 Ops/s $\textbf{\color{#35bf28}+7.39\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 5.6973ms 4.3855ms 228.0224 Ops/s 219.7830 Ops/s $\color{#35bf28}+3.75\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.9956ms 2.4695ms 404.9374 Ops/s 404.1312 Ops/s $\color{#35bf28}+0.20\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.9815ms 1.4710ms 679.8062 Ops/s 667.7036 Ops/s $\color{#35bf28}+1.81\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 11.3926ms 11.0719ms 90.3189 Ops/s 87.1684 Ops/s $\color{#35bf28}+3.61\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 16.0155ms 14.4448ms 69.2292 Ops/s 69.0301 Ops/s $\color{#35bf28}+0.29\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.3898ms 19.7658ms 50.5924 Ops/s 50.0547 Ops/s $\color{#35bf28}+1.07\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 15.0852ms 14.5400ms 68.7758 Ops/s 68.3544 Ops/s $\color{#35bf28}+0.62\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 20.3834ms 19.5044ms 51.2704 Ops/s 50.2818 Ops/s $\color{#35bf28}+1.97\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 16.9520ms 15.6340ms 63.9630 Ops/s 63.7364 Ops/s $\color{#35bf28}+0.36\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Dec 3, 2024

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}17$. Worsened: $\large\color{#d91a1a}10$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7508s 0.7495s 1.3343 Ops/s 1.3005 Ops/s $\color{#35bf28}+2.60\%$
test_transformed 1.0943s 1.0140s 0.9862 Ops/s 0.9806 Ops/s $\color{#35bf28}+0.57\%$
test_serial 2.2285s 2.1485s 0.4654 Ops/s 0.4614 Ops/s $\color{#35bf28}+0.87\%$
test_parallel 2.0837s 1.9777s 0.5056 Ops/s 0.4983 Ops/s $\color{#35bf28}+1.46\%$
test_step_mdp_speed[True-True-True-True-True] 0.4086ms 40.1585μs 24.9014 KOps/s 25.4117 KOps/s $\color{#d91a1a}-2.01\%$
test_step_mdp_speed[True-True-True-True-False] 82.2810μs 22.1985μs 45.0482 KOps/s 43.2500 KOps/s $\color{#35bf28}+4.16\%$
test_step_mdp_speed[True-True-True-False-True] 60.7100μs 22.2086μs 45.0276 KOps/s 46.3535 KOps/s $\color{#d91a1a}-2.86\%$
test_step_mdp_speed[True-True-True-False-False] 42.5000μs 12.8860μs 77.6039 KOps/s 77.5349 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[True-True-False-True-True] 95.3010μs 42.4843μs 23.5381 KOps/s 23.5410 KOps/s $\color{#d91a1a}-0.01\%$
test_step_mdp_speed[True-True-False-True-False] 59.0910μs 24.7894μs 40.3398 KOps/s 39.9975 KOps/s $\color{#35bf28}+0.86\%$
test_step_mdp_speed[True-True-False-False-True] 57.3610μs 24.4035μs 40.9778 KOps/s 41.4242 KOps/s $\color{#d91a1a}-1.08\%$
test_step_mdp_speed[True-True-False-False-False] 0.1706ms 15.1447μs 66.0296 KOps/s 67.3462 KOps/s $\color{#d91a1a}-1.95\%$
test_step_mdp_speed[True-False-True-True-True] 86.7610μs 44.7250μs 22.3588 KOps/s 22.4407 KOps/s $\color{#d91a1a}-0.36\%$
test_step_mdp_speed[True-False-True-True-False] 64.9510μs 27.3290μs 36.5912 KOps/s 36.0591 KOps/s $\color{#35bf28}+1.48\%$
test_step_mdp_speed[True-False-True-False-True] 59.7710μs 24.8332μs 40.2687 KOps/s 43.0954 KOps/s $\textbf{\color{#d91a1a}-6.56\%}$
test_step_mdp_speed[True-False-True-False-False] 54.5910μs 14.9352μs 66.9561 KOps/s 66.4058 KOps/s $\color{#35bf28}+0.83\%$
test_step_mdp_speed[True-False-False-True-True] 88.4420μs 46.6306μs 21.4452 KOps/s 21.5304 KOps/s $\color{#d91a1a}-0.40\%$
test_step_mdp_speed[True-False-False-True-False] 63.2710μs 29.0172μs 34.4624 KOps/s 34.1392 KOps/s $\color{#35bf28}+0.95\%$
test_step_mdp_speed[True-False-False-False-True] 62.5310μs 26.1285μs 38.2724 KOps/s 38.7602 KOps/s $\color{#d91a1a}-1.26\%$
test_step_mdp_speed[True-False-False-False-False] 59.4810μs 17.0114μs 58.7842 KOps/s 58.0722 KOps/s $\color{#35bf28}+1.23\%$
test_step_mdp_speed[False-True-True-True-True] 81.8910μs 44.0503μs 22.7013 KOps/s 22.5592 KOps/s $\color{#35bf28}+0.63\%$
test_step_mdp_speed[False-True-True-True-False] 62.9910μs 27.3987μs 36.4980 KOps/s 36.8927 KOps/s $\color{#d91a1a}-1.07\%$
test_step_mdp_speed[False-True-True-False-True] 73.9110μs 27.9130μs 35.8256 KOps/s 36.2103 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-True-True-False-False] 50.4610μs 16.5414μs 60.4542 KOps/s 59.5181 KOps/s $\color{#35bf28}+1.57\%$
test_step_mdp_speed[False-True-False-True-True] 82.2510μs 46.2623μs 21.6159 KOps/s 21.5982 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[False-True-False-True-False] 0.2219ms 28.9285μs 34.5680 KOps/s 34.0028 KOps/s $\color{#35bf28}+1.66\%$
test_step_mdp_speed[False-True-False-False-True] 3.2458ms 30.3052μs 32.9976 KOps/s 32.7886 KOps/s $\color{#35bf28}+0.64\%$
test_step_mdp_speed[False-True-False-False-False] 50.4510μs 18.7863μs 53.2302 KOps/s 53.3000 KOps/s $\color{#d91a1a}-0.13\%$
test_step_mdp_speed[False-False-True-True-True] 0.2460ms 48.9948μs 20.4103 KOps/s 20.1988 KOps/s $\color{#35bf28}+1.05\%$
test_step_mdp_speed[False-False-True-True-False] 70.9710μs 31.5174μs 31.7285 KOps/s 31.1471 KOps/s $\color{#35bf28}+1.87\%$
test_step_mdp_speed[False-False-True-False-True] 67.2310μs 29.9855μs 33.3494 KOps/s 33.3025 KOps/s $\color{#35bf28}+0.14\%$
test_step_mdp_speed[False-False-True-False-False] 52.6210μs 18.5811μs 53.8183 KOps/s 53.8425 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[False-False-False-True-True] 98.8220μs 49.9273μs 20.0291 KOps/s 20.0454 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[False-False-False-True-False] 63.7310μs 33.1859μs 30.1333 KOps/s 29.8284 KOps/s $\color{#35bf28}+1.02\%$
test_step_mdp_speed[False-False-False-False-True] 65.5810μs 31.3903μs 31.8570 KOps/s 31.8836 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[False-False-False-False-False] 57.4600μs 20.8214μs 48.0275 KOps/s 47.7241 KOps/s $\color{#35bf28}+0.64\%$
test_values[generalized_advantage_estimate-True-True] 25.6805ms 24.9448ms 40.0885 Ops/s 40.4815 Ops/s $\color{#d91a1a}-0.97\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1054s 3.0089ms 332.3421 Ops/s 315.1727 Ops/s $\textbf{\color{#35bf28}+5.45\%}$
test_values[td0_return_estimate-False-False] 0.1061ms 81.7610μs 12.2308 KOps/s 12.1575 KOps/s $\color{#35bf28}+0.60\%$
test_values[td1_return_estimate-False-False] 58.3197ms 55.7616ms 17.9335 Ops/s 18.1141 Ops/s $\color{#d91a1a}-1.00\%$
test_values[vec_td1_return_estimate-False-False] 1.2572ms 1.0819ms 924.2884 Ops/s 922.6964 Ops/s $\color{#35bf28}+0.17\%$
test_values[td_lambda_return_estimate-True-False] 89.6270ms 88.2087ms 11.3367 Ops/s 11.0423 Ops/s $\color{#35bf28}+2.67\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2172ms 1.0749ms 930.3331 Ops/s 927.6560 Ops/s $\color{#35bf28}+0.29\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 26.4224ms 24.6421ms 40.5809 Ops/s 40.8777 Ops/s $\color{#d91a1a}-0.73\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0473ms 0.7554ms 1.3238 KOps/s 1.3278 KOps/s $\color{#d91a1a}-0.31\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.9026ms 0.6752ms 1.4811 KOps/s 1.4822 KOps/s $\color{#d91a1a}-0.08\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6566ms 1.4874ms 672.3134 Ops/s 673.0157 Ops/s $\color{#d91a1a}-0.10\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7240ms 0.6873ms 1.4550 KOps/s 1.4379 KOps/s $\color{#35bf28}+1.19\%$
test_dqn_speed[False-None] 7.1922ms 1.4754ms 677.8013 Ops/s 669.7693 Ops/s $\color{#35bf28}+1.20\%$
test_dqn_speed[False-backward] 2.2870ms 2.1084ms 474.2957 Ops/s 475.9227 Ops/s $\color{#d91a1a}-0.34\%$
test_dqn_speed[True-None] 0.7408ms 0.5395ms 1.8536 KOps/s 1.8705 KOps/s $\color{#d91a1a}-0.90\%$
test_dqn_speed[True-backward] 1.3263ms 1.2429ms 804.5586 Ops/s 903.3959 Ops/s $\textbf{\color{#d91a1a}-10.94\%}$
test_dqn_speed[reduce-overhead-None] 0.6977ms 0.5508ms 1.8157 KOps/s 1.8246 KOps/s $\color{#d91a1a}-0.49\%$
test_dqn_speed[reduce-overhead-backward] 1.2199ms 1.0830ms 923.3512 Ops/s 1.0192 KOps/s $\textbf{\color{#d91a1a}-9.40\%}$
test_ddpg_speed[False-None] 3.0570ms 2.7733ms 360.5875 Ops/s 353.4302 Ops/s $\color{#35bf28}+2.03\%$
test_ddpg_speed[False-backward] 4.6269ms 4.1610ms 240.3272 Ops/s 246.3886 Ops/s $\color{#d91a1a}-2.46\%$
test_ddpg_speed[True-None] 1.2350ms 1.0773ms 928.2321 Ops/s 907.6140 Ops/s $\color{#35bf28}+2.27\%$
test_ddpg_speed[True-backward] 2.3944ms 2.3061ms 433.6322 Ops/s 430.9786 Ops/s $\color{#35bf28}+0.62\%$
test_ddpg_speed[reduce-overhead-None] 1.2331ms 1.0916ms 916.0702 Ops/s 888.4139 Ops/s $\color{#35bf28}+3.11\%$
test_ddpg_speed[reduce-overhead-backward] 1.8760ms 1.7884ms 559.1539 Ops/s 555.7719 Ops/s $\color{#35bf28}+0.61\%$
test_sac_speed[False-None] 8.4461ms 7.9566ms 125.6820 Ops/s 122.8645 Ops/s $\color{#35bf28}+2.29\%$
test_sac_speed[False-backward] 11.7341ms 11.2798ms 88.6540 Ops/s 88.2965 Ops/s $\color{#35bf28}+0.40\%$
test_sac_speed[True-None] 1.7402ms 1.5430ms 648.1065 Ops/s 648.3273 Ops/s $\color{#d91a1a}-0.03\%$
test_sac_speed[True-backward] 3.3749ms 3.2470ms 307.9720 Ops/s 307.8983 Ops/s $\color{#35bf28}+0.02\%$
test_sac_speed[reduce-overhead-None] 22.4816ms 12.3703ms 80.8387 Ops/s 79.7829 Ops/s $\color{#35bf28}+1.32\%$
test_sac_speed[reduce-overhead-backward] 1.6659ms 1.5202ms 657.7882 Ops/s 740.1442 Ops/s $\textbf{\color{#d91a1a}-11.13\%}$
test_redq_speed[False-None] 8.4776ms 7.5807ms 131.9131 Ops/s 131.8902 Ops/s $\color{#35bf28}+0.02\%$
test_redq_speed[False-backward] 12.6550ms 11.7577ms 85.0510 Ops/s 86.9393 Ops/s $\color{#d91a1a}-2.17\%$
test_redq_speed[True-None] 2.2191ms 1.9814ms 504.6999 Ops/s 500.2166 Ops/s $\color{#35bf28}+0.90\%$
test_redq_speed[True-backward] 3.9925ms 3.9009ms 256.3528 Ops/s 269.2347 Ops/s $\color{#d91a1a}-4.78\%$
test_redq_speed[reduce-overhead-None] 2.3112ms 2.0501ms 487.7838 Ops/s 497.4583 Ops/s $\color{#d91a1a}-1.94\%$
test_redq_speed[reduce-overhead-backward] 3.9377ms 3.8516ms 259.6331 Ops/s 269.5168 Ops/s $\color{#d91a1a}-3.67\%$
test_redq_deprec_speed[False-None] 9.5997ms 9.0493ms 110.5053 Ops/s 110.2231 Ops/s $\color{#35bf28}+0.26\%$
test_redq_deprec_speed[False-backward] 13.0096ms 12.4397ms 80.3881 Ops/s 82.0955 Ops/s $\color{#d91a1a}-2.08\%$
test_redq_deprec_speed[True-None] 2.4698ms 2.3138ms 432.1885 Ops/s 432.2067 Ops/s $-0.00\%$
test_redq_deprec_speed[True-backward] 4.1531ms 3.9739ms 251.6429 Ops/s 239.3747 Ops/s $\textbf{\color{#35bf28}+5.13\%}$
test_redq_deprec_speed[reduce-overhead-None] 2.5110ms 2.3150ms 431.9566 Ops/s 431.4052 Ops/s $\color{#35bf28}+0.13\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.6745ms 4.2420ms 235.7397 Ops/s 238.7321 Ops/s $\color{#d91a1a}-1.25\%$
test_td3_speed[False-None] 8.2832ms 7.9678ms 125.5054 Ops/s 119.5530 Ops/s $\color{#35bf28}+4.98\%$
test_td3_speed[False-backward] 11.0126ms 10.5156ms 95.0970 Ops/s 94.5070 Ops/s $\color{#35bf28}+0.62\%$
test_td3_speed[True-None] 1.5955ms 1.5698ms 637.0068 Ops/s 641.9221 Ops/s $\color{#d91a1a}-0.77\%$
test_td3_speed[True-backward] 3.3887ms 3.2740ms 305.4350 Ops/s 302.7474 Ops/s $\color{#35bf28}+0.89\%$
test_td3_speed[reduce-overhead-None] 48.9495ms 25.0728ms 39.8839 Ops/s 37.1444 Ops/s $\textbf{\color{#35bf28}+7.38\%}$
test_td3_speed[reduce-overhead-backward] 1.5991ms 1.4573ms 686.2003 Ops/s 753.8030 Ops/s $\textbf{\color{#d91a1a}-8.97\%}$
test_cql_speed[False-None] 16.4178ms 16.0713ms 62.2227 Ops/s 61.4896 Ops/s $\color{#35bf28}+1.19\%$
test_cql_speed[False-backward] 22.5157ms 21.7543ms 45.9680 Ops/s 46.4581 Ops/s $\color{#d91a1a}-1.05\%$
test_cql_speed[True-None] 3.0823ms 2.9112ms 343.4966 Ops/s 341.5739 Ops/s $\color{#35bf28}+0.56\%$
test_cql_speed[True-backward] 5.4715ms 5.0738ms 197.0927 Ops/s 190.7027 Ops/s $\color{#35bf28}+3.35\%$
test_cql_speed[reduce-overhead-None] 20.9470ms 12.8608ms 77.7556 Ops/s 76.2702 Ops/s $\color{#35bf28}+1.95\%$
test_cql_speed[reduce-overhead-backward] 1.8183ms 1.6894ms 591.9295 Ops/s 598.5523 Ops/s $\color{#d91a1a}-1.11\%$
test_a2c_speed[False-None] 3.5560ms 3.1560ms 316.8592 Ops/s 312.4870 Ops/s $\color{#35bf28}+1.40\%$
test_a2c_speed[False-backward] 7.0756ms 6.3409ms 157.7063 Ops/s 156.3027 Ops/s $\color{#35bf28}+0.90\%$
test_a2c_speed[True-None] 1.3610ms 0.9929ms 1.0071 KOps/s 1.0002 KOps/s $\color{#35bf28}+0.69\%$
test_a2c_speed[True-backward] 3.1230ms 2.7738ms 360.5142 Ops/s 355.0046 Ops/s $\color{#35bf28}+1.55\%$
test_a2c_speed[reduce-overhead-None] 0.3964s 12.2168ms 81.8547 Ops/s 86.8770 Ops/s $\textbf{\color{#d91a1a}-5.78\%}$
test_a2c_speed[reduce-overhead-backward] 1.2200ms 1.1475ms 871.4239 Ops/s 876.8813 Ops/s $\color{#d91a1a}-0.62\%$
test_ppo_speed[False-None] 4.0228ms 3.6230ms 276.0150 Ops/s 271.3819 Ops/s $\color{#35bf28}+1.71\%$
test_ppo_speed[False-backward] 7.4847ms 7.1102ms 140.6423 Ops/s 140.8180 Ops/s $\color{#d91a1a}-0.12\%$
test_ppo_speed[True-None] 1.3197ms 0.9367ms 1.0676 KOps/s 1.0455 KOps/s $\color{#35bf28}+2.12\%$
test_ppo_speed[True-backward] 2.8225ms 2.7516ms 363.4228 Ops/s 366.9116 Ops/s $\color{#d91a1a}-0.95\%$
test_ppo_speed[reduce-overhead-None] 0.9067ms 0.4929ms 2.0289 KOps/s 1.8902 KOps/s $\textbf{\color{#35bf28}+7.33\%}$
test_ppo_speed[reduce-overhead-backward] 1.1953ms 1.1413ms 876.1958 Ops/s 870.6681 Ops/s $\color{#35bf28}+0.63\%$
test_reinforce_speed[False-None] 2.6360ms 2.2279ms 448.8515 Ops/s 444.5744 Ops/s $\color{#35bf28}+0.96\%$
test_reinforce_speed[False-backward] 3.7387ms 3.3367ms 299.6978 Ops/s 295.4687 Ops/s $\color{#35bf28}+1.43\%$
test_reinforce_speed[True-None] 1.1817ms 0.8193ms 1.2206 KOps/s 1.2046 KOps/s $\color{#35bf28}+1.33\%$
test_reinforce_speed[True-backward] 2.5819ms 2.4485ms 408.4139 Ops/s 388.4581 Ops/s $\textbf{\color{#35bf28}+5.14\%}$
test_reinforce_speed[reduce-overhead-None] 22.3647ms 11.6709ms 85.6834 Ops/s 87.0517 Ops/s $\color{#d91a1a}-1.57\%$
test_reinforce_speed[reduce-overhead-backward] 1.0980ms 1.0653ms 938.7426 Ops/s 832.1311 Ops/s $\textbf{\color{#35bf28}+12.81\%}$
test_iql_speed[False-None] 9.7174ms 9.1363ms 109.4538 Ops/s 108.5583 Ops/s $\color{#35bf28}+0.82\%$
test_iql_speed[False-backward] 13.6220ms 13.0438ms 76.6645 Ops/s 75.8481 Ops/s $\color{#35bf28}+1.08\%$
test_iql_speed[True-None] 1.9251ms 1.7534ms 570.3146 Ops/s 579.1777 Ops/s $\color{#d91a1a}-1.53\%$
test_iql_speed[True-backward] 4.3405ms 4.2427ms 235.7004 Ops/s 225.4355 Ops/s $\color{#35bf28}+4.55\%$
test_iql_speed[reduce-overhead-None] 20.2773ms 11.4127ms 87.6215 Ops/s 87.5682 Ops/s $\color{#35bf28}+0.06\%$
test_iql_speed[reduce-overhead-backward] 1.6024ms 1.4489ms 690.1869 Ops/s 653.4068 Ops/s $\textbf{\color{#35bf28}+5.63\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9056ms 6.4213ms 155.7328 Ops/s 153.5701 Ops/s $\color{#35bf28}+1.41\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5720ms 0.3262ms 3.0658 KOps/s 3.0171 KOps/s $\color{#35bf28}+1.61\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6577ms 0.3506ms 2.8523 KOps/s 3.4997 KOps/s $\textbf{\color{#d91a1a}-18.50\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.0416ms 6.1456ms 162.7193 Ops/s 160.9231 Ops/s $\color{#35bf28}+1.12\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.5791ms 0.2833ms 3.5299 KOps/s 3.4293 KOps/s $\color{#35bf28}+2.93\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5687ms 0.3311ms 3.0200 KOps/s 4.1243 KOps/s $\textbf{\color{#d91a1a}-26.78\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7676ms 1.4114ms 708.5335 Ops/s 689.3933 Ops/s $\color{#35bf28}+2.78\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.8335ms 1.3593ms 735.6756 Ops/s 711.5235 Ops/s $\color{#35bf28}+3.39\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.7505ms 6.3421ms 157.6754 Ops/s 157.9082 Ops/s $\color{#d91a1a}-0.15\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.2262ms 0.4579ms 2.1837 KOps/s 2.3208 KOps/s $\textbf{\color{#d91a1a}-5.91\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6028ms 0.3873ms 2.5822 KOps/s 2.5444 KOps/s $\color{#35bf28}+1.49\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.5846ms 6.1882ms 161.5986 Ops/s 160.2645 Ops/s $\color{#35bf28}+0.83\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.2116ms 0.2751ms 3.6346 KOps/s 3.0624 KOps/s $\textbf{\color{#35bf28}+18.68\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4636ms 0.2495ms 4.0074 KOps/s 3.1087 KOps/s $\textbf{\color{#35bf28}+28.91\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.6383ms 6.1743ms 161.9629 Ops/s 161.5345 Ops/s $\color{#35bf28}+0.27\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.5846ms 0.3448ms 2.8999 KOps/s 2.6340 KOps/s $\textbf{\color{#35bf28}+10.10\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5378ms 0.2970ms 3.3665 KOps/s 2.7656 KOps/s $\textbf{\color{#35bf28}+21.73\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.6711ms 6.3341ms 157.8752 Ops/s 157.5941 Ops/s $\color{#35bf28}+0.18\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0948ms 0.4103ms 2.4371 KOps/s 1.9250 KOps/s $\textbf{\color{#35bf28}+26.60\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7993ms 0.3879ms 2.5778 KOps/s 1.9977 KOps/s $\textbf{\color{#35bf28}+29.03\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.9604ms 5.2975ms 188.7688 Ops/s 190.7098 Ops/s $\color{#d91a1a}-1.02\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 10.1059ms 2.0750ms 481.9181 Ops/s 439.3628 Ops/s $\textbf{\color{#35bf28}+9.69\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.0303ms 1.2284ms 814.0916 Ops/s 783.6991 Ops/s $\color{#35bf28}+3.88\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.5046s 15.3049ms 65.3384 Ops/s 191.9889 Ops/s $\textbf{\color{#d91a1a}-65.97\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 10.5008ms 2.0848ms 479.6586 Ops/s 441.7820 Ops/s $\textbf{\color{#35bf28}+8.57\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 3.5290ms 1.1727ms 852.7633 Ops/s 861.3428 Ops/s $\color{#d91a1a}-1.00\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 9.2564ms 5.5985ms 178.6180 Ops/s 33.3663 Ops/s $\textbf{\color{#35bf28}+435.32\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 7.9617ms 2.1817ms 458.3554 Ops/s 472.9276 Ops/s $\color{#d91a1a}-3.08\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 8.9112ms 1.4513ms 689.0571 Ops/s 724.9864 Ops/s $\color{#d91a1a}-4.96\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.3843ms 13.0999ms 76.3362 Ops/s 75.3128 Ops/s $\color{#35bf28}+1.36\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.6747ms 17.0331ms 58.7093 Ops/s 58.4135 Ops/s $\color{#35bf28}+0.51\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 17.7461ms 17.3469ms 57.6471 Ops/s 54.4165 Ops/s $\textbf{\color{#35bf28}+5.94\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 17.7665ms 17.1467ms 58.3202 Ops/s 59.4652 Ops/s $\color{#d91a1a}-1.93\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 17.6932ms 17.4167ms 57.4162 Ops/s 55.0953 Ops/s $\color{#35bf28}+4.21\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.1973ms 18.4116ms 54.3135 Ops/s 55.4329 Ops/s $\color{#d91a1a}-2.02\%$

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
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