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 slice sampler compatibility with split_trajs and MultiStep #1961

Merged
merged 4 commits into from
Feb 24, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 24, 2024

No description provided.

Copy link

pytorch-bot bot commented Feb 24, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1961

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

✅ You can merge normally! (1 Unrelated Failure)

As of commit beb4f0f with merge base 7782751 (image):

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 24, 2024
Copy link

github-actions bot commented Feb 24, 2024

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}2$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1159s 0.1131s 8.8443 Ops/s 8.4502 Ops/s $\color{#35bf28}+4.66\%$
test_sync 96.2679ms 95.8852ms 10.4291 Ops/s 9.8711 Ops/s $\textbf{\color{#35bf28}+5.65\%}$
test_async 0.1811s 91.7274ms 10.9019 Ops/s 10.9403 Ops/s $\color{#d91a1a}-0.35\%$
test_single_pixels 0.1284s 0.1256s 7.9627 Ops/s 7.5983 Ops/s $\color{#35bf28}+4.80\%$
test_sync_pixels 82.3146ms 79.8213ms 12.5280 Ops/s 12.5398 Ops/s $\color{#d91a1a}-0.09\%$
test_async_pixels 0.1465s 75.7437ms 13.2024 Ops/s 15.1284 Ops/s $\textbf{\color{#d91a1a}-12.73\%}$
test_simple 0.8705s 0.8152s 1.2268 Ops/s 1.2203 Ops/s $\color{#35bf28}+0.53\%$
test_transformed 1.0858s 1.0310s 0.9699 Ops/s 0.9616 Ops/s $\color{#35bf28}+0.86\%$
test_serial 2.4415s 2.3651s 0.4228 Ops/s 0.4151 Ops/s $\color{#35bf28}+1.87\%$
test_parallel 2.1133s 2.0426s 0.4896 Ops/s 0.4804 Ops/s $\color{#35bf28}+1.92\%$
test_step_mdp_speed[True-True-True-True-True] 85.1010μs 32.1832μs 31.0721 KOps/s 30.8976 KOps/s $\color{#35bf28}+0.57\%$
test_step_mdp_speed[True-True-True-True-False] 45.5310μs 19.3738μs 51.6161 KOps/s 50.6105 KOps/s $\color{#35bf28}+1.99\%$
test_step_mdp_speed[True-True-True-False-True] 36.1200μs 18.3873μs 54.3854 KOps/s 54.2174 KOps/s $\color{#35bf28}+0.31\%$
test_step_mdp_speed[True-True-True-False-False] 25.4610μs 10.9417μs 91.3939 KOps/s 91.0212 KOps/s $\color{#35bf28}+0.41\%$
test_step_mdp_speed[True-True-False-True-True] 58.5910μs 34.1669μs 29.2681 KOps/s 29.2850 KOps/s $\color{#d91a1a}-0.06\%$
test_step_mdp_speed[True-True-False-True-False] 37.8500μs 21.0342μs 47.5417 KOps/s 46.4492 KOps/s $\color{#35bf28}+2.35\%$
test_step_mdp_speed[True-True-False-False-True] 46.2710μs 20.1815μs 49.5502 KOps/s 49.2318 KOps/s $\color{#35bf28}+0.65\%$
test_step_mdp_speed[True-True-False-False-False] 31.3110μs 12.8495μs 77.8238 KOps/s 76.7705 KOps/s $\color{#35bf28}+1.37\%$
test_step_mdp_speed[True-False-True-True-True] 51.5420μs 35.3416μs 28.2953 KOps/s 27.2559 KOps/s $\color{#35bf28}+3.81\%$
test_step_mdp_speed[True-False-True-True-False] 40.2210μs 23.0744μs 43.3381 KOps/s 42.1156 KOps/s $\color{#35bf28}+2.90\%$
test_step_mdp_speed[True-False-True-False-True] 38.1210μs 19.9395μs 50.1518 KOps/s 49.2703 KOps/s $\color{#35bf28}+1.79\%$
test_step_mdp_speed[True-False-True-False-False] 29.8910μs 12.7722μs 78.2949 KOps/s 77.7962 KOps/s $\color{#35bf28}+0.64\%$
test_step_mdp_speed[True-False-False-True-True] 61.9320μs 37.2097μs 26.8747 KOps/s 26.6081 KOps/s $\color{#35bf28}+1.00\%$
test_step_mdp_speed[True-False-False-True-False] 38.3810μs 24.8217μs 40.2873 KOps/s 39.4824 KOps/s $\color{#35bf28}+2.04\%$
test_step_mdp_speed[True-False-False-False-True] 38.2100μs 21.6605μs 46.1669 KOps/s 45.8185 KOps/s $\color{#35bf28}+0.76\%$
test_step_mdp_speed[True-False-False-False-False] 30.1510μs 14.6545μs 68.2384 KOps/s 67.9455 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[False-True-True-True-True] 57.1000μs 35.8004μs 27.9326 KOps/s 27.4272 KOps/s $\color{#35bf28}+1.84\%$
test_step_mdp_speed[False-True-True-True-False] 47.9700μs 23.3006μs 42.9173 KOps/s 42.6310 KOps/s $\color{#35bf28}+0.67\%$
test_step_mdp_speed[False-True-True-False-True] 65.2710μs 23.8417μs 41.9433 KOps/s 41.4743 KOps/s $\color{#35bf28}+1.13\%$
test_step_mdp_speed[False-True-True-False-False] 33.1300μs 14.6454μs 68.2809 KOps/s 67.4402 KOps/s $\color{#35bf28}+1.25\%$
test_step_mdp_speed[False-True-False-True-True] 61.3510μs 37.5838μs 26.6072 KOps/s 25.9304 KOps/s $\color{#35bf28}+2.61\%$
test_step_mdp_speed[False-True-False-True-False] 60.5410μs 24.9162μs 40.1345 KOps/s 39.3646 KOps/s $\color{#35bf28}+1.96\%$
test_step_mdp_speed[False-True-False-False-True] 47.3300μs 25.5686μs 39.1105 KOps/s 38.5804 KOps/s $\color{#35bf28}+1.37\%$
test_step_mdp_speed[False-True-False-False-False] 33.5400μs 16.2827μs 61.4148 KOps/s 59.7513 KOps/s $\color{#35bf28}+2.78\%$
test_step_mdp_speed[False-False-True-True-True] 95.1010μs 39.3611μs 25.4058 KOps/s 25.0564 KOps/s $\color{#35bf28}+1.39\%$
test_step_mdp_speed[False-False-True-True-False] 44.0400μs 26.6477μs 37.5267 KOps/s 36.7510 KOps/s $\color{#35bf28}+2.11\%$
test_step_mdp_speed[False-False-True-False-True] 47.7010μs 25.5940μs 39.0717 KOps/s 38.0399 KOps/s $\color{#35bf28}+2.71\%$
test_step_mdp_speed[False-False-True-False-False] 31.6200μs 16.2913μs 61.3824 KOps/s 59.2641 KOps/s $\color{#35bf28}+3.57\%$
test_step_mdp_speed[False-False-False-True-True] 62.4500μs 40.8946μs 24.4531 KOps/s 24.1227 KOps/s $\color{#35bf28}+1.37\%$
test_step_mdp_speed[False-False-False-True-False] 52.6700μs 28.6453μs 34.9097 KOps/s 34.5812 KOps/s $\color{#35bf28}+0.95\%$
test_step_mdp_speed[False-False-False-False-True] 47.7110μs 27.1994μs 36.7656 KOps/s 36.3654 KOps/s $\color{#35bf28}+1.10\%$
test_step_mdp_speed[False-False-False-False-False] 32.7510μs 18.0438μs 55.4206 KOps/s 54.1809 KOps/s $\color{#35bf28}+2.29\%$
test_values[generalized_advantage_estimate-True-True] 24.9032ms 24.3059ms 41.1423 Ops/s 41.9568 Ops/s $\color{#d91a1a}-1.94\%$
test_values[vec_generalized_advantage_estimate-True-True] 88.7009ms 3.3302ms 300.2823 Ops/s 311.2473 Ops/s $\color{#d91a1a}-3.52\%$
test_values[td0_return_estimate-False-False] 0.1008ms 60.1834μs 16.6159 KOps/s 17.0022 KOps/s $\color{#d91a1a}-2.27\%$
test_values[td1_return_estimate-False-False] 52.6573ms 52.1798ms 19.1645 Ops/s 19.3922 Ops/s $\color{#d91a1a}-1.17\%$
test_values[vec_td1_return_estimate-False-False] 2.0396ms 1.7485ms 571.9131 Ops/s 573.4616 Ops/s $\color{#d91a1a}-0.27\%$
test_values[td_lambda_return_estimate-True-False] 88.8242ms 86.4229ms 11.5710 Ops/s 12.1318 Ops/s $\color{#d91a1a}-4.62\%$
test_values[vec_td_lambda_return_estimate-True-False] 3.9929ms 1.7876ms 559.4003 Ops/s 538.7746 Ops/s $\color{#35bf28}+3.83\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.1162ms 22.9382ms 43.5955 Ops/s 43.7415 Ops/s $\color{#d91a1a}-0.33\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8964ms 0.6925ms 1.4441 KOps/s 1.4675 KOps/s $\color{#d91a1a}-1.59\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7031ms 0.6412ms 1.5597 KOps/s 1.5554 KOps/s $\color{#35bf28}+0.27\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.4946ms 1.4435ms 692.7512 Ops/s 696.4873 Ops/s $\color{#d91a1a}-0.54\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9208ms 0.6610ms 1.5129 KOps/s 1.5252 KOps/s $\color{#d91a1a}-0.80\%$
test_dqn_speed 9.1529ms 1.4503ms 689.5290 Ops/s 683.1285 Ops/s $\color{#35bf28}+0.94\%$
test_ddpg_speed 2.9247ms 2.7661ms 361.5188 Ops/s 353.1284 Ops/s $\color{#35bf28}+2.38\%$
test_sac_speed 8.4314ms 7.9843ms 125.2462 Ops/s 123.3537 Ops/s $\color{#35bf28}+1.53\%$
test_redq_speed 16.2110ms 10.0839ms 99.1682 Ops/s 98.4559 Ops/s $\color{#35bf28}+0.72\%$
test_redq_deprec_speed 12.0533ms 11.2611ms 88.8014 Ops/s 89.5900 Ops/s $\color{#d91a1a}-0.88\%$
test_td3_speed 15.9924ms 8.0810ms 123.7471 Ops/s 121.5684 Ops/s $\color{#35bf28}+1.79\%$
test_cql_speed 25.9193ms 24.9878ms 40.0195 Ops/s 39.6864 Ops/s $\color{#35bf28}+0.84\%$
test_a2c_speed 5.7015ms 5.4576ms 183.2301 Ops/s 181.6982 Ops/s $\color{#35bf28}+0.84\%$
test_ppo_speed 7.0751ms 5.8238ms 171.7095 Ops/s 172.4392 Ops/s $\color{#d91a1a}-0.42\%$
test_reinforce_speed 4.8207ms 4.5682ms 218.9029 Ops/s 221.0183 Ops/s $\color{#d91a1a}-0.96\%$
test_iql_speed 20.0808ms 19.2486ms 51.9519 Ops/s 51.9200 Ops/s $\color{#35bf28}+0.06\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0055ms 2.8494ms 350.9484 Ops/s 353.8885 Ops/s $\color{#d91a1a}-0.83\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 90.1956ms 0.5947ms 1.6816 KOps/s 1.8526 KOps/s $\textbf{\color{#d91a1a}-9.23\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6830ms 0.5061ms 1.9759 KOps/s 1.9412 KOps/s $\color{#35bf28}+1.79\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.7799ms 2.8752ms 347.8039 Ops/s 347.6370 Ops/s $\color{#35bf28}+0.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2390ms 0.5286ms 1.8918 KOps/s 1.8944 KOps/s $\color{#d91a1a}-0.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6528ms 0.5033ms 1.9871 KOps/s 1.9657 KOps/s $\color{#35bf28}+1.09\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.0947ms 2.9771ms 335.8942 Ops/s 337.0112 Ops/s $\color{#d91a1a}-0.33\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2524ms 0.6543ms 1.5284 KOps/s 1.5134 KOps/s $\color{#35bf28}+0.99\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8152ms 0.6307ms 1.5854 KOps/s 1.5787 KOps/s $\color{#35bf28}+0.42\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.1762ms 2.8759ms 347.7116 Ops/s 352.8312 Ops/s $\color{#d91a1a}-1.45\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1322ms 0.5310ms 1.8834 KOps/s 1.8563 KOps/s $\color{#35bf28}+1.46\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6757ms 0.5117ms 1.9544 KOps/s 1.9492 KOps/s $\color{#35bf28}+0.27\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.2070ms 2.8861ms 346.4857 Ops/s 347.0278 Ops/s $\color{#d91a1a}-0.16\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1900ms 0.5239ms 1.9089 KOps/s 1.8789 KOps/s $\color{#35bf28}+1.60\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6621ms 0.5044ms 1.9827 KOps/s 1.9740 KOps/s $\color{#35bf28}+0.44\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1527ms 3.0066ms 332.5978 Ops/s 337.5563 Ops/s $\color{#d91a1a}-1.47\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2473ms 0.6538ms 1.5296 KOps/s 1.5224 KOps/s $\color{#35bf28}+0.48\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8094ms 0.6294ms 1.5888 KOps/s 1.5729 KOps/s $\color{#35bf28}+1.01\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1217s 8.8635ms 112.8219 Ops/s 111.7117 Ops/s $\color{#35bf28}+0.99\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.6551ms 14.4505ms 69.2018 Ops/s 68.3973 Ops/s $\color{#35bf28}+1.18\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.2594ms 1.1371ms 879.4621 Ops/s 973.5339 Ops/s $\textbf{\color{#d91a1a}-9.66\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 99.4706ms 6.5600ms 152.4382 Ops/s 116.5588 Ops/s $\textbf{\color{#35bf28}+30.78\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.1109s 16.3148ms 61.2940 Ops/s 68.5068 Ops/s $\textbf{\color{#d91a1a}-10.53\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.9803ms 1.2370ms 808.4384 Ops/s 957.6401 Ops/s $\textbf{\color{#d91a1a}-15.58\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 99.8972ms 6.9111ms 144.6951 Ops/s 142.5526 Ops/s $\color{#35bf28}+1.50\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.0083ms 14.5860ms 68.5587 Ops/s 67.2122 Ops/s $\color{#35bf28}+2.00\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.0362ms 1.5796ms 633.0633 Ops/s 693.6797 Ops/s $\textbf{\color{#d91a1a}-8.74\%}$

Copy link

github-actions bot commented Feb 24, 2024

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}8$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 63.1589ms 61.3664ms 16.2956 Ops/s 16.4029 Ops/s $\color{#d91a1a}-0.65\%$
test_sync 41.4672ms 33.4653ms 29.8817 Ops/s 30.1738 Ops/s $\color{#d91a1a}-0.97\%$
test_async 55.1513ms 30.6374ms 32.6399 Ops/s 30.4135 Ops/s $\textbf{\color{#35bf28}+7.32\%}$
test_simple 0.4836s 0.4309s 2.3209 Ops/s 2.2714 Ops/s $\color{#35bf28}+2.18\%$
test_transformed 0.6402s 0.5931s 1.6859 Ops/s 1.7330 Ops/s $\color{#d91a1a}-2.71\%$
test_serial 1.4783s 1.4330s 0.6978 Ops/s 0.7021 Ops/s $\color{#d91a1a}-0.60\%$
test_parallel 1.4362s 1.3818s 0.7237 Ops/s 0.7194 Ops/s $\color{#35bf28}+0.59\%$
test_step_mdp_speed[True-True-True-True-True] 94.0340μs 20.9527μs 47.7265 KOps/s 46.9186 KOps/s $\color{#35bf28}+1.72\%$
test_step_mdp_speed[True-True-True-True-False] 68.9080μs 12.8629μs 77.7429 KOps/s 76.5983 KOps/s $\color{#35bf28}+1.49\%$
test_step_mdp_speed[True-True-True-False-True] 33.5230μs 12.3711μs 80.8332 KOps/s 78.3253 KOps/s $\color{#35bf28}+3.20\%$
test_step_mdp_speed[True-True-True-False-False] 49.3520μs 7.6223μs 131.1936 KOps/s 131.1641 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[True-True-False-True-True] 46.7670μs 22.6224μs 44.2041 KOps/s 43.6781 KOps/s $\color{#35bf28}+1.20\%$
test_step_mdp_speed[True-True-False-True-False] 58.4590μs 14.3633μs 69.6219 KOps/s 69.3849 KOps/s $\color{#35bf28}+0.34\%$
test_step_mdp_speed[True-True-False-False-True] 39.2630μs 13.6526μs 73.2462 KOps/s 71.9670 KOps/s $\color{#35bf28}+1.78\%$
test_step_mdp_speed[True-True-False-False-False] 48.7110μs 8.8794μs 112.6196 KOps/s 112.2022 KOps/s $\color{#35bf28}+0.37\%$
test_step_mdp_speed[True-False-True-True-True] 55.5530μs 23.7831μs 42.0467 KOps/s 41.4509 KOps/s $\color{#35bf28}+1.44\%$
test_step_mdp_speed[True-False-True-True-False] 59.3510μs 15.5199μs 64.4334 KOps/s 64.3306 KOps/s $\color{#35bf28}+0.16\%$
test_step_mdp_speed[True-False-True-False-True] 48.1300μs 13.7948μs 72.4909 KOps/s 72.4339 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[True-False-True-False-False] 25.1670μs 8.9153μs 112.1665 KOps/s 113.2778 KOps/s $\color{#d91a1a}-0.98\%$
test_step_mdp_speed[True-False-False-True-True] 66.1150μs 25.1231μs 39.8040 KOps/s 39.3794 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[True-False-False-True-False] 37.0990μs 16.9025μs 59.1630 KOps/s 59.6043 KOps/s $\color{#d91a1a}-0.74\%$
test_step_mdp_speed[True-False-False-False-True] 48.8710μs 14.8956μs 67.1338 KOps/s 66.4264 KOps/s $\color{#35bf28}+1.06\%$
test_step_mdp_speed[True-False-False-False-False] 40.0250μs 10.0495μs 99.5076 KOps/s 99.0923 KOps/s $\color{#35bf28}+0.42\%$
test_step_mdp_speed[False-True-True-True-True] 58.1890μs 23.8288μs 41.9660 KOps/s 41.6381 KOps/s $\color{#35bf28}+0.79\%$
test_step_mdp_speed[False-True-True-True-False] 38.7530μs 15.7407μs 63.5297 KOps/s 64.1773 KOps/s $\color{#d91a1a}-1.01\%$
test_step_mdp_speed[False-True-True-False-True] 60.3330μs 15.9764μs 62.5925 KOps/s 62.3687 KOps/s $\color{#35bf28}+0.36\%$
test_step_mdp_speed[False-True-True-False-False] 33.0520μs 10.2414μs 97.6434 KOps/s 97.5859 KOps/s $\color{#35bf28}+0.06\%$
test_step_mdp_speed[False-True-False-True-True] 37.7500μs 25.6542μs 38.9800 KOps/s 39.0854 KOps/s $\color{#d91a1a}-0.27\%$
test_step_mdp_speed[False-True-False-True-False] 61.0740μs 16.7855μs 59.5753 KOps/s 59.0387 KOps/s $\color{#35bf28}+0.91\%$
test_step_mdp_speed[False-True-False-False-True] 44.6230μs 17.0937μs 58.5012 KOps/s 56.8005 KOps/s $\color{#35bf28}+2.99\%$
test_step_mdp_speed[False-True-False-False-False] 60.6330μs 11.2978μs 88.5126 KOps/s 88.7578 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[False-False-True-True-True] 78.0760μs 26.6640μs 37.5038 KOps/s 37.3462 KOps/s $\color{#35bf28}+0.42\%$
test_step_mdp_speed[False-False-True-True-False] 39.3530μs 18.4068μs 54.3277 KOps/s 54.5572 KOps/s $\color{#d91a1a}-0.42\%$
test_step_mdp_speed[False-False-True-False-True] 62.9180μs 17.2616μs 57.9321 KOps/s 57.5529 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[False-False-True-False-False] 35.5360μs 11.6622μs 85.7468 KOps/s 88.0999 KOps/s $\color{#d91a1a}-2.67\%$
test_step_mdp_speed[False-False-False-True-True] 74.2290μs 27.7534μs 36.0317 KOps/s 36.1205 KOps/s $\color{#d91a1a}-0.25\%$
test_step_mdp_speed[False-False-False-True-False] 70.1000μs 19.3725μs 51.6196 KOps/s 51.5252 KOps/s $\color{#35bf28}+0.18\%$
test_step_mdp_speed[False-False-False-False-True] 40.0940μs 18.3840μs 54.3952 KOps/s 54.0665 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[False-False-False-False-False] 49.2920μs 12.4822μs 80.1141 KOps/s 80.9948 KOps/s $\color{#d91a1a}-1.09\%$
test_values[generalized_advantage_estimate-True-True] 14.1043ms 9.8543ms 101.4784 Ops/s 108.6688 Ops/s $\textbf{\color{#d91a1a}-6.62\%}$
test_values[vec_generalized_advantage_estimate-True-True] 36.7597ms 33.2526ms 30.0728 Ops/s 30.0602 Ops/s $\color{#35bf28}+0.04\%$
test_values[td0_return_estimate-False-False] 0.2376ms 0.1629ms 6.1378 KOps/s 6.0394 KOps/s $\color{#35bf28}+1.63\%$
test_values[td1_return_estimate-False-False] 23.5266ms 23.2398ms 43.0295 Ops/s 43.7105 Ops/s $\color{#d91a1a}-1.56\%$
test_values[vec_td1_return_estimate-False-False] 34.2375ms 33.2970ms 30.0327 Ops/s 30.1440 Ops/s $\color{#d91a1a}-0.37\%$
test_values[td_lambda_return_estimate-True-False] 36.5352ms 33.6886ms 29.6837 Ops/s 29.8572 Ops/s $\color{#d91a1a}-0.58\%$
test_values[vec_td_lambda_return_estimate-True-False] 35.2532ms 33.3626ms 29.9737 Ops/s 30.0177 Ops/s $\color{#d91a1a}-0.15\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 9.8576ms 8.1455ms 122.7679 Ops/s 123.0755 Ops/s $\color{#d91a1a}-0.25\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.0848ms 1.8186ms 549.8823 Ops/s 508.3708 Ops/s $\textbf{\color{#35bf28}+8.17\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5008ms 0.3519ms 2.8420 KOps/s 2.8574 KOps/s $\color{#d91a1a}-0.54\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 41.0875ms 39.0250ms 25.6246 Ops/s 25.7729 Ops/s $\color{#d91a1a}-0.58\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.6056ms 3.0017ms 333.1427 Ops/s 330.7081 Ops/s $\color{#35bf28}+0.74\%$
test_dqn_speed 7.0037ms 1.3863ms 721.3524 Ops/s 726.0328 Ops/s $\color{#d91a1a}-0.64\%$
test_ddpg_speed 3.4783ms 2.7515ms 363.4328 Ops/s 359.6916 Ops/s $\color{#35bf28}+1.04\%$
test_sac_speed 72.4381ms 8.8216ms 113.3577 Ops/s 120.7546 Ops/s $\textbf{\color{#d91a1a}-6.13\%}$
test_redq_speed 13.8995ms 12.9559ms 77.1852 Ops/s 75.7182 Ops/s $\color{#35bf28}+1.94\%$
test_redq_deprec_speed 14.3269ms 13.2223ms 75.6299 Ops/s 77.1879 Ops/s $\color{#d91a1a}-2.02\%$
test_td3_speed 8.5527ms 8.2794ms 120.7813 Ops/s 120.6217 Ops/s $\color{#35bf28}+0.13\%$
test_cql_speed 38.2832ms 36.1850ms 27.6358 Ops/s 27.7110 Ops/s $\color{#d91a1a}-0.27\%$
test_a2c_speed 8.0050ms 7.2985ms 137.0136 Ops/s 135.8930 Ops/s $\color{#35bf28}+0.82\%$
test_ppo_speed 9.0030ms 7.6186ms 131.2585 Ops/s 131.5717 Ops/s $\color{#d91a1a}-0.24\%$
test_reinforce_speed 7.3462ms 6.5332ms 153.0653 Ops/s 151.4956 Ops/s $\color{#35bf28}+1.04\%$
test_iql_speed 33.5680ms 32.2657ms 30.9927 Ops/s 29.7184 Ops/s $\color{#35bf28}+4.29\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.3157ms 2.1137ms 473.1129 Ops/s 448.0454 Ops/s $\textbf{\color{#35bf28}+5.59\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7781ms 0.4880ms 2.0491 KOps/s 2.0149 KOps/s $\color{#35bf28}+1.70\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 3.3463ms 0.4610ms 2.1691 KOps/s 2.1316 KOps/s $\color{#35bf28}+1.76\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.3231ms 2.0883ms 478.8676 Ops/s 466.8266 Ops/s $\color{#35bf28}+2.58\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9169ms 0.4829ms 2.0710 KOps/s 2.0775 KOps/s $\color{#d91a1a}-0.31\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7144ms 0.4576ms 2.1855 KOps/s 1.8659 KOps/s $\textbf{\color{#35bf28}+17.13\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.3237ms 2.2177ms 450.9137 Ops/s 436.9475 Ops/s $\color{#35bf28}+3.20\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0260ms 0.5986ms 1.6707 KOps/s 1.6506 KOps/s $\color{#35bf28}+1.22\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9442ms 0.5709ms 1.7515 KOps/s 1.6825 KOps/s $\color{#35bf28}+4.10\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.5935ms 2.1645ms 461.9920 Ops/s 429.9329 Ops/s $\textbf{\color{#35bf28}+7.46\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9784ms 0.4868ms 2.0544 KOps/s 1.6635 KOps/s $\textbf{\color{#35bf28}+23.50\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7128ms 0.4643ms 2.1537 KOps/s 2.1082 KOps/s $\color{#35bf28}+2.16\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.4839ms 2.1086ms 474.2547 Ops/s 447.6644 Ops/s $\textbf{\color{#35bf28}+5.94\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9090ms 0.4798ms 2.0842 KOps/s 2.0840 KOps/s $+0.01\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7207ms 0.4609ms 2.1695 KOps/s 2.1591 KOps/s $\color{#35bf28}+0.48\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.3514ms 2.2224ms 449.9582 Ops/s 442.5735 Ops/s $\color{#35bf28}+1.67\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7799ms 0.5980ms 1.6723 KOps/s 1.6636 KOps/s $\color{#35bf28}+0.52\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 89.9063ms 0.6738ms 1.4842 KOps/s 1.7186 KOps/s $\textbf{\color{#d91a1a}-13.64\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 85.1141ms 5.1976ms 192.3956 Ops/s 178.8289 Ops/s $\textbf{\color{#35bf28}+7.59\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.7478ms 11.9000ms 84.0337 Ops/s 84.3758 Ops/s $\color{#d91a1a}-0.41\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.6449ms 1.0238ms 976.7173 Ops/s 961.5835 Ops/s $\color{#35bf28}+1.57\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 88.8945ms 6.9057ms 144.8089 Ops/s 141.1463 Ops/s $\color{#35bf28}+2.59\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.7689ms 11.8839ms 84.1471 Ops/s 84.4190 Ops/s $\color{#d91a1a}-0.32\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.7180ms 1.0266ms 974.0614 Ops/s 967.6804 Ops/s $\color{#35bf28}+0.66\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 88.7099ms 7.2545ms 137.8447 Ops/s 177.1252 Ops/s $\textbf{\color{#d91a1a}-22.18\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 14.7632ms 12.2028ms 81.9487 Ops/s 81.7594 Ops/s $\color{#35bf28}+0.23\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.0415ms 1.3485ms 741.5910 Ops/s 740.0406 Ops/s $\color{#35bf28}+0.21\%$

@vmoens vmoens marked this pull request as ready for review February 24, 2024 02:52
@vmoens vmoens merged commit 249b811 into main Feb 24, 2024
67 of 68 checks passed
@vmoens vmoens deleted the fix-slicesampling branch February 27, 2024 00:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
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
Development

Successfully merging this pull request may close these issues.

2 participants