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

[Minor] Missing commit from #1488 #1490

Merged
merged 4 commits into from
Sep 5, 2023
Merged

[Minor] Missing commit from #1488 #1490

merged 4 commits into from
Sep 5, 2023

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Sep 5, 2023

No description provided.

@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 Sep 5, 2023
# Conflicts:
#	torchrl/modules/distributions/discrete.py
@vmoens vmoens added bug Something isn't working documentation Improvements or additions to documentation labels Sep 5, 2023
@vmoens vmoens merged commit deb6e6e into main Sep 5, 2023
@vmoens vmoens deleted the masked_onehot branch September 5, 2023 15:00
@github-actions
Copy link

github-actions bot commented Sep 5, 2023

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

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

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1399s 0.1393s 7.1808 Ops/s 7.0654 Ops/s $\color{#35bf28}+1.63\%$
test_sync 0.1674s 83.1694ms 12.0236 Ops/s 12.0768 Ops/s $\color{#d91a1a}-0.44\%$
test_async 0.2164s 74.0101ms 13.5117 Ops/s 13.6610 Ops/s $\color{#d91a1a}-1.09\%$
test_simple 0.7247s 0.6312s 1.5843 Ops/s 1.5566 Ops/s $\color{#35bf28}+1.77\%$
test_transformed 1.7230s 1.6421s 0.6090 Ops/s 0.6097 Ops/s $\color{#d91a1a}-0.12\%$
test_serial 1.8232s 1.7340s 0.5767 Ops/s 0.5626 Ops/s $\color{#35bf28}+2.50\%$
test_parallel 1.5889s 1.5044s 0.6647 Ops/s 0.6740 Ops/s $\color{#d91a1a}-1.38\%$
test_step_mdp_speed[True-True-True-True-True] 0.1715ms 45.2325μs 22.1080 KOps/s 22.3047 KOps/s $\color{#d91a1a}-0.88\%$
test_step_mdp_speed[True-True-True-True-False] 55.3010μs 25.8111μs 38.7430 KOps/s 39.3566 KOps/s $\color{#d91a1a}-1.56\%$
test_step_mdp_speed[True-True-True-False-True] 62.1020μs 31.8864μs 31.3614 KOps/s 31.8528 KOps/s $\color{#d91a1a}-1.54\%$
test_step_mdp_speed[True-True-True-False-False] 68.4020μs 17.7190μs 56.4365 KOps/s 57.3304 KOps/s $\color{#d91a1a}-1.56\%$
test_step_mdp_speed[True-True-False-True-True] 87.1030μs 46.7625μs 21.3847 KOps/s 21.4322 KOps/s $\color{#d91a1a}-0.22\%$
test_step_mdp_speed[True-True-False-True-False] 0.1071ms 27.7667μs 36.0144 KOps/s 36.5617 KOps/s $\color{#d91a1a}-1.50\%$
test_step_mdp_speed[True-True-False-False-True] 61.3020μs 33.9136μs 29.4867 KOps/s 30.0686 KOps/s $\color{#d91a1a}-1.94\%$
test_step_mdp_speed[True-True-False-False-False] 0.1014ms 20.0691μs 49.8278 KOps/s 51.1919 KOps/s $\color{#d91a1a}-2.66\%$
test_step_mdp_speed[True-False-True-True-True] 0.1227ms 48.8016μs 20.4911 KOps/s 20.4014 KOps/s $\color{#35bf28}+0.44\%$
test_step_mdp_speed[True-False-True-True-False] 0.1162ms 29.8123μs 33.5433 KOps/s 34.1255 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[True-False-True-False-True] 86.1020μs 33.7564μs 29.6240 KOps/s 29.9354 KOps/s $\color{#d91a1a}-1.04\%$
test_step_mdp_speed[True-False-True-False-False] 0.1031ms 20.3274μs 49.1947 KOps/s 50.9459 KOps/s $\color{#d91a1a}-3.44\%$
test_step_mdp_speed[True-False-False-True-True] 84.4020μs 50.1533μs 19.9389 KOps/s 19.9543 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[True-False-False-True-False] 0.1209ms 31.1408μs 32.1122 KOps/s 32.1286 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[True-False-False-False-True] 77.0020μs 35.6782μs 28.0283 KOps/s 28.6618 KOps/s $\color{#d91a1a}-2.21\%$
test_step_mdp_speed[True-False-False-False-False] 55.6020μs 21.6751μs 46.1359 KOps/s 47.4095 KOps/s $\color{#d91a1a}-2.69\%$
test_step_mdp_speed[False-True-True-True-True] 95.3030μs 49.0689μs 20.3795 KOps/s 20.5549 KOps/s $\color{#d91a1a}-0.85\%$
test_step_mdp_speed[False-True-True-True-False] 71.7020μs 29.4662μs 33.9371 KOps/s 33.9143 KOps/s $\color{#35bf28}+0.07\%$
test_step_mdp_speed[False-True-True-False-True] 90.2020μs 38.2738μs 26.1275 KOps/s 26.6706 KOps/s $\color{#d91a1a}-2.04\%$
test_step_mdp_speed[False-True-True-False-False] 4.5584ms 22.1974μs 45.0502 KOps/s 46.1930 KOps/s $\color{#d91a1a}-2.47\%$
test_step_mdp_speed[False-True-False-True-True] 0.1329ms 50.9983μs 19.6085 KOps/s 19.8701 KOps/s $\color{#d91a1a}-1.32\%$
test_step_mdp_speed[False-True-False-True-False] 63.7020μs 31.2223μs 32.0284 KOps/s 32.1544 KOps/s $\color{#d91a1a}-0.39\%$
test_step_mdp_speed[False-True-False-False-True] 0.1322ms 40.2081μs 24.8706 KOps/s 25.7463 KOps/s $\color{#d91a1a}-3.40\%$
test_step_mdp_speed[False-True-False-False-False] 58.0020μs 23.7258μs 42.1482 KOps/s 43.3773 KOps/s $\color{#d91a1a}-2.83\%$
test_step_mdp_speed[False-False-True-True-True] 0.1547ms 52.4478μs 19.0666 KOps/s 19.1496 KOps/s $\color{#d91a1a}-0.43\%$
test_step_mdp_speed[False-False-True-True-False] 62.2020μs 33.1577μs 30.1589 KOps/s 30.4670 KOps/s $\color{#d91a1a}-1.01\%$
test_step_mdp_speed[False-False-True-False-True] 97.7020μs 39.5237μs 25.3013 KOps/s 25.6057 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[False-False-True-False-False] 60.1010μs 23.7940μs 42.0274 KOps/s 43.3219 KOps/s $\color{#d91a1a}-2.99\%$
test_step_mdp_speed[False-False-False-True-True] 0.1821ms 53.5054μs 18.6897 KOps/s 18.6088 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[False-False-False-True-False] 95.0020μs 35.1305μs 28.4653 KOps/s 29.2853 KOps/s $\color{#d91a1a}-2.80\%$
test_step_mdp_speed[False-False-False-False-True] 0.1440ms 40.4672μs 24.7114 KOps/s 24.5498 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[False-False-False-False-False] 2.2422ms 25.7595μs 38.8207 KOps/s 40.6031 KOps/s $\color{#d91a1a}-4.39\%$
test_values[generalized_advantage_estimate-True-True] 17.7868ms 14.4129ms 69.3824 Ops/s 70.0417 Ops/s $\color{#d91a1a}-0.94\%$
test_values[vec_generalized_advantage_estimate-True-True] 52.4033ms 45.3860ms 22.0332 Ops/s 21.3777 Ops/s $\color{#35bf28}+3.07\%$
test_values[td0_return_estimate-False-False] 0.4041ms 0.2870ms 3.4839 KOps/s 3.3289 KOps/s $\color{#35bf28}+4.66\%$
test_values[td1_return_estimate-False-False] 14.5569ms 13.8673ms 72.1119 Ops/s 72.0215 Ops/s $\color{#35bf28}+0.13\%$
test_values[vec_td1_return_estimate-False-False] 62.6040ms 46.3504ms 21.5748 Ops/s 20.9627 Ops/s $\color{#35bf28}+2.92\%$
test_values[td_lambda_return_estimate-True-False] 34.8307ms 33.0431ms 30.2635 Ops/s 30.1406 Ops/s $\color{#35bf28}+0.41\%$
test_values[vec_td_lambda_return_estimate-True-False] 63.4494ms 46.3147ms 21.5914 Ops/s 21.2914 Ops/s $\color{#35bf28}+1.41\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 12.1247ms 11.9471ms 83.7022 Ops/s 84.7495 Ops/s $\color{#d91a1a}-1.24\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 7.0414ms 3.6038ms 277.4882 Ops/s 287.1544 Ops/s $\color{#d91a1a}-3.37\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 2.9583ms 0.4927ms 2.0297 KOps/s 1.8705 KOps/s $\textbf{\color{#35bf28}+8.51\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 72.3043ms 63.2295ms 15.8154 Ops/s 16.3353 Ops/s $\color{#d91a1a}-3.18\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.9562ms 3.1850ms 313.9680 Ops/s 307.7974 Ops/s $\color{#35bf28}+2.00\%$
test_dqn_speed 6.2995ms 1.9205ms 520.7107 Ops/s 484.5938 Ops/s $\textbf{\color{#35bf28}+7.45\%}$
test_ddpg_speed 18.2602ms 2.9193ms 342.5535 Ops/s 331.1726 Ops/s $\color{#35bf28}+3.44\%$
test_sac_speed 0.1619s 16.1178ms 62.0433 Ops/s 109.2969 Ops/s $\textbf{\color{#d91a1a}-43.23\%}$
test_redq_speed 26.0896ms 18.6803ms 53.5323 Ops/s 53.5451 Ops/s $\color{#d91a1a}-0.02\%$
test_redq_deprec_speed 22.3261ms 15.5279ms 64.4002 Ops/s 66.4634 Ops/s $\color{#d91a1a}-3.10\%$
test_td3_speed 13.4430ms 12.1578ms 82.2514 Ops/s 88.2834 Ops/s $\textbf{\color{#d91a1a}-6.83\%}$
test_cql_speed 52.7043ms 39.2520ms 25.4764 Ops/s 31.7156 Ops/s $\textbf{\color{#d91a1a}-19.67\%}$
test_a2c_speed 14.8722ms 7.5549ms 132.3641 Ops/s 170.8244 Ops/s $\textbf{\color{#d91a1a}-22.51\%}$
test_ppo_speed 18.5719ms 8.4642ms 118.1450 Ops/s 162.3096 Ops/s $\textbf{\color{#d91a1a}-27.21\%}$
test_reinforce_speed 14.9368ms 5.8555ms 170.7802 Ops/s 236.7438 Ops/s $\textbf{\color{#d91a1a}-27.86\%}$
test_iql_speed 34.4169ms 27.8594ms 35.8946 Ops/s 41.6622 Ops/s $\textbf{\color{#d91a1a}-13.84\%}$
test_sample_rb[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.3598ms 3.0136ms 331.8258 Ops/s 337.0175 Ops/s $\color{#d91a1a}-1.54\%$
test_sample_rb[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 7.4590ms 3.1980ms 312.6963 Ops/s 318.7443 Ops/s $\color{#d91a1a}-1.90\%$
test_sample_rb[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 7.2752ms 3.1868ms 313.7973 Ops/s 323.2788 Ops/s $\color{#d91a1a}-2.93\%$
test_sample_rb[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.7007ms 3.0280ms 330.2528 Ops/s 334.4642 Ops/s $\color{#d91a1a}-1.26\%$
test_sample_rb[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 6.0586ms 3.1345ms 319.0280 Ops/s 318.7190 Ops/s $\color{#35bf28}+0.10\%$
test_sample_rb[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 6.2733ms 3.1372ms 318.7511 Ops/s 323.2088 Ops/s $\color{#d91a1a}-1.38\%$
test_sample_rb[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.5920ms 2.9677ms 336.9566 Ops/s 335.9396 Ops/s $\color{#35bf28}+0.30\%$
test_sample_rb[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.1874s 3.7091ms 269.6039 Ops/s 316.4110 Ops/s $\textbf{\color{#d91a1a}-14.79\%}$
test_sample_rb[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 6.8761ms 3.1319ms 319.2946 Ops/s 309.0284 Ops/s $\color{#35bf28}+3.32\%$
test_iterate_rb[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.8570ms 2.9626ms 337.5455 Ops/s 322.6424 Ops/s $\color{#35bf28}+4.62\%$
test_iterate_rb[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 6.4361ms 3.1291ms 319.5838 Ops/s 314.7660 Ops/s $\color{#35bf28}+1.53\%$
test_iterate_rb[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 5.6595ms 3.1331ms 319.1722 Ops/s 318.1496 Ops/s $\color{#35bf28}+0.32\%$
test_iterate_rb[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8884ms 3.0136ms 331.8257 Ops/s 325.6087 Ops/s $\color{#35bf28}+1.91\%$
test_iterate_rb[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 5.9498ms 3.1356ms 318.9202 Ops/s 314.6612 Ops/s $\color{#35bf28}+1.35\%$
test_iterate_rb[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 6.2344ms 3.1463ms 317.8374 Ops/s 316.1828 Ops/s $\color{#35bf28}+0.52\%$
test_iterate_rb[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.4540ms 2.9782ms 335.7750 Ops/s 328.6064 Ops/s $\color{#35bf28}+2.18\%$
test_iterate_rb[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 5.4981ms 3.1288ms 319.6065 Ops/s 313.3374 Ops/s $\color{#35bf28}+2.00\%$
test_iterate_rb[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 6.6862ms 3.1534ms 317.1182 Ops/s 315.5407 Ops/s $\color{#35bf28}+0.50\%$
test_populate_rb[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.3658s 35.5945ms 28.0943 Ops/s 28.3721 Ops/s $\color{#d91a1a}-0.98\%$
test_populate_rb[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 0.2294s 36.2666ms 27.5736 Ops/s 28.3473 Ops/s $\color{#d91a1a}-2.73\%$
test_populate_rb[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 0.2034s 32.1138ms 31.1393 Ops/s 31.7513 Ops/s $\color{#d91a1a}-1.93\%$
test_populate_rb[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.2032s 35.7647ms 27.9605 Ops/s 28.1803 Ops/s $\color{#d91a1a}-0.78\%$
test_populate_rb[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.2011s 31.7599ms 31.4862 Ops/s 31.5076 Ops/s $\color{#d91a1a}-0.07\%$
test_populate_rb[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 0.2031s 31.6881ms 31.5576 Ops/s 28.6312 Ops/s $\textbf{\color{#35bf28}+10.22\%}$
test_populate_rb[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1930s 31.2281ms 32.0224 Ops/s 31.6400 Ops/s $\color{#35bf28}+1.21\%$
test_populate_rb[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1985s 34.9988ms 28.5724 Ops/s 28.6214 Ops/s $\color{#d91a1a}-0.17\%$
test_populate_rb[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 0.1960s 31.6297ms 31.6158 Ops/s 28.7249 Ops/s $\textbf{\color{#35bf28}+10.06\%}$

vmoens added a commit to hyerra/rl that referenced this pull request Oct 10, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. documentation Improvements or additions to documentation
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants