-
Notifications
You must be signed in to change notification settings - Fork 328
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
[Test] Test state_dict and loss modules #1527
Merged
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 14, 2023
matteobettini
approved these changes
Sep 14, 2023
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
|
Name | Max | Mean | Ops | Ops on Repo HEAD
|
Change |
---|---|---|---|---|---|
test_single | 74.1498ms | 73.4676ms | 13.6114 Ops/s | 13.6853 Ops/s | |
test_sync | 0.1174s | 43.2681ms | 23.1117 Ops/s | 22.9656 Ops/s | |
test_async | 0.1233s | 40.4018ms | 24.7514 Ops/s | 25.0717 Ops/s | |
test_simple | 0.6908s | 0.6193s | 1.6146 Ops/s | 1.5961 Ops/s | |
test_transformed | 0.8357s | 0.7898s | 1.2661 Ops/s | 1.2479 Ops/s | |
test_serial | 1.7763s | 1.7151s | 0.5830 Ops/s | 0.5751 Ops/s | |
test_parallel | 1.6320s | 1.5450s | 0.6473 Ops/s | 0.6705 Ops/s | |
test_step_mdp_speed[True-True-True-True-True] | 0.1908ms | 44.4822μs | 22.4809 KOps/s | 22.2425 KOps/s | |
test_step_mdp_speed[True-True-True-True-False] | 63.2000μs | 25.5911μs | 39.0762 KOps/s | 39.5944 KOps/s | |
test_step_mdp_speed[True-True-True-False-True] | 57.9010μs | 31.4197μs | 31.8272 KOps/s | 31.6973 KOps/s | |
test_step_mdp_speed[True-True-True-False-False] | 45.5010μs | 17.5600μs | 56.9476 KOps/s | 56.9217 KOps/s | |
test_step_mdp_speed[True-True-False-True-True] | 73.8010μs | 46.0908μs | 21.6963 KOps/s | 21.6462 KOps/s | |
test_step_mdp_speed[True-True-False-True-False] | 71.5010μs | 27.1506μs | 36.8316 KOps/s | 36.8478 KOps/s | |
test_step_mdp_speed[True-True-False-False-True] | 58.1010μs | 33.3646μs | 29.9719 KOps/s | 29.6487 KOps/s | |
test_step_mdp_speed[True-True-False-False-False] | 63.5010μs | 19.6049μs | 51.0078 KOps/s | 51.2607 KOps/s | |
test_step_mdp_speed[True-False-True-True-True] | 72.6010μs | 48.0380μs | 20.8169 KOps/s | 20.6361 KOps/s | |
test_step_mdp_speed[True-False-True-True-False] | 96.7010μs | 29.1145μs | 34.3472 KOps/s | 34.1523 KOps/s | |
test_step_mdp_speed[True-False-True-False-True] | 57.6010μs | 33.3059μs | 30.0247 KOps/s | 29.8111 KOps/s | |
test_step_mdp_speed[True-False-True-False-False] | 0.2061ms | 19.7896μs | 50.5317 KOps/s | 51.4702 KOps/s | |
test_step_mdp_speed[True-False-False-True-True] | 0.1250ms | 49.4990μs | 20.2024 KOps/s | 20.1621 KOps/s | |
test_step_mdp_speed[True-False-False-True-False] | 92.3010μs | 30.8482μs | 32.4168 KOps/s | 32.3106 KOps/s | |
test_step_mdp_speed[True-False-False-False-True] | 54.9010μs | 34.9752μs | 28.5917 KOps/s | 28.8471 KOps/s | |
test_step_mdp_speed[True-False-False-False-False] | 54.9010μs | 21.4403μs | 46.6412 KOps/s | 47.0897 KOps/s | |
test_step_mdp_speed[False-True-True-True-True] | 75.0010μs | 47.8169μs | 20.9131 KOps/s | 20.7795 KOps/s | |
test_step_mdp_speed[False-True-True-True-False] | 96.3010μs | 29.3084μs | 34.1199 KOps/s | 34.0197 KOps/s | |
test_step_mdp_speed[False-True-True-False-True] | 0.1130ms | 37.1135μs | 26.9444 KOps/s | 26.8822 KOps/s | |
test_step_mdp_speed[False-True-True-False-False] | 3.3618ms | 21.6943μs | 46.0951 KOps/s | 45.4859 KOps/s | |
test_step_mdp_speed[False-True-False-True-True] | 78.5010μs | 49.4293μs | 20.2309 KOps/s | 20.1209 KOps/s | |
test_step_mdp_speed[False-True-False-True-False] | 52.9010μs | 30.7134μs | 32.5591 KOps/s | 32.1567 KOps/s | |
test_step_mdp_speed[False-True-False-False-True] | 89.1010μs | 38.6143μs | 25.8972 KOps/s | 25.8216 KOps/s | |
test_step_mdp_speed[False-True-False-False-False] | 0.3775ms | 23.3459μs | 42.8341 KOps/s | 42.2889 KOps/s | |
test_step_mdp_speed[False-False-True-True-True] | 98.9010μs | 52.0999μs | 19.1939 KOps/s | 19.4556 KOps/s | |
test_step_mdp_speed[False-False-True-True-False] | 67.6010μs | 32.5604μs | 30.7122 KOps/s | 30.3836 KOps/s | |
test_step_mdp_speed[False-False-True-False-True] | 89.8010μs | 39.1806μs | 25.5229 KOps/s | 25.9457 KOps/s | |
test_step_mdp_speed[False-False-True-False-False] | 74.4010μs | 23.3706μs | 42.7888 KOps/s | 42.7245 KOps/s | |
test_step_mdp_speed[False-False-False-True-True] | 86.6010μs | 52.8386μs | 18.9256 KOps/s | 18.9603 KOps/s | |
test_step_mdp_speed[False-False-False-True-False] | 63.9010μs | 33.9816μs | 29.4277 KOps/s | 29.0462 KOps/s | |
test_step_mdp_speed[False-False-False-False-True] | 83.0010μs | 40.3752μs | 24.7677 KOps/s | 24.7818 KOps/s | |
test_step_mdp_speed[False-False-False-False-False] | 47.8010μs | 24.8591μs | 40.2268 KOps/s | 40.3326 KOps/s | |
test_values[generalized_advantage_estimate-True-True] | 15.6447ms | 14.0503ms | 71.1731 Ops/s | 71.1997 Ops/s | |
test_values[vec_generalized_advantage_estimate-True-True] | 46.0222ms | 40.7492ms | 24.5404 Ops/s | 23.7624 Ops/s | |
test_values[td0_return_estimate-False-False] | 0.4491ms | 0.2010ms | 4.9754 KOps/s | 5.1559 KOps/s | |
test_values[td1_return_estimate-False-False] | 13.9960ms | 13.6740ms | 73.1315 Ops/s | 74.5302 Ops/s | |
test_values[vec_td1_return_estimate-False-False] | 46.1648ms | 40.9839ms | 24.3998 Ops/s | 24.1025 Ops/s | |
test_values[td_lambda_return_estimate-True-False] | 37.8114ms | 32.9748ms | 30.3262 Ops/s | 30.7027 Ops/s | |
test_values[vec_td_lambda_return_estimate-True-False] | 46.5087ms | 41.6838ms | 23.9902 Ops/s | 23.7383 Ops/s | |
test_gae_speed[generalized_advantage_estimate-False-1-512] | 15.8057ms | 12.2723ms | 81.4843 Ops/s | 80.9560 Ops/s | |
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] | 5.5875ms | 3.3654ms | 297.1444 Ops/s | 303.8898 Ops/s | |
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] | 6.6550ms | 0.4853ms | 2.0605 KOps/s | 2.1701 KOps/s | |
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] | 59.7372ms | 55.4786ms | 18.0250 Ops/s | 17.3819 Ops/s | |
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] | 3.5001ms | 2.8966ms | 345.2270 Ops/s | 359.6085 Ops/s | |
test_dqn_speed | 7.8476ms | 1.8621ms | 537.0316 Ops/s | 486.5256 Ops/s | |
test_ddpg_speed | 8.4730ms | 2.8220ms | 354.3603 Ops/s | 359.9958 Ops/s | |
test_sac_speed | 16.5088ms | 8.5636ms | 116.7728 Ops/s | 121.0420 Ops/s | |
test_redq_speed | 28.8888ms | 17.3439ms | 57.6573 Ops/s | 61.1037 Ops/s | |
test_redq_deprec_speed | 18.9700ms | 13.6569ms | 73.2230 Ops/s | 77.2015 Ops/s | |
test_td3_speed | 11.8437ms | 10.3545ms | 96.5766 Ops/s | 98.6611 Ops/s | |
test_cql_speed | 37.0919ms | 28.2992ms | 35.3366 Ops/s | 37.4596 Ops/s | |
test_a2c_speed | 11.9366ms | 5.4535ms | 183.3677 Ops/s | 189.8489 Ops/s | |
test_ppo_speed | 11.6516ms | 5.8491ms | 170.9668 Ops/s | 180.7691 Ops/s | |
test_reinforce_speed | 9.4274ms | 4.2027ms | 237.9426 Ops/s | 239.3049 Ops/s | |
test_iql_speed | 30.1413ms | 22.1366ms | 45.1740 Ops/s | 46.5045 Ops/s | |
test_sample_rb[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 3.3789ms | 2.6509ms | 377.2323 Ops/s | 374.9553 Ops/s | |
test_sample_rb[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 3.8653ms | 2.7856ms | 358.9872 Ops/s | 360.9474 Ops/s | |
test_sample_rb[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 0.1517s | 3.2885ms | 304.0934 Ops/s | 353.3019 Ops/s | |
test_sample_rb[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 2.9589ms | 2.6690ms | 374.6734 Ops/s | 382.1700 Ops/s | |
test_sample_rb[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 4.4310ms | 2.8561ms | 350.1279 Ops/s | 347.6927 Ops/s | |
test_sample_rb[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 6.0098ms | 2.8999ms | 344.8423 Ops/s | 350.6989 Ops/s | |
test_sample_rb[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 3.7727ms | 2.7486ms | 363.8221 Ops/s | 381.6543 Ops/s | |
test_sample_rb[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 5.1897ms | 2.8717ms | 348.2278 Ops/s | 356.8805 Ops/s | |
test_sample_rb[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 0.1473s | 3.3069ms | 302.4003 Ops/s | 357.6752 Ops/s | |
test_iterate_rb[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 3.8248ms | 2.7456ms | 364.2131 Ops/s | 375.6836 Ops/s | |
test_iterate_rb[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 4.3147ms | 2.8942ms | 345.5244 Ops/s | 341.8177 Ops/s | |
test_iterate_rb[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 4.8153ms | 2.8879ms | 346.2750 Ops/s | 356.9951 Ops/s | |
test_iterate_rb[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 3.7288ms | 2.6871ms | 372.1431 Ops/s | 290.4150 Ops/s | |
test_iterate_rb[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 4.6629ms | 2.7792ms | 359.8165 Ops/s | 356.4535 Ops/s | |
test_iterate_rb[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 6.0237ms | 2.9028ms | 344.4938 Ops/s | 348.5298 Ops/s | |
test_iterate_rb[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 3.5560ms | 2.7074ms | 369.3535 Ops/s | 378.8372 Ops/s | |
test_iterate_rb[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 5.1763ms | 2.8764ms | 347.6529 Ops/s | 351.6251 Ops/s | |
test_iterate_rb[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 4.4463ms | 2.8579ms | 349.9027 Ops/s | 361.8547 Ops/s | |
test_populate_rb[TensorDictReplayBuffer-ListStorage-RandomSampler-400] | 0.2364s | 31.7021ms | 31.5436 Ops/s | 33.8884 Ops/s | |
test_populate_rb[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] | 0.1464s | 27.2321ms | 36.7214 Ops/s | 34.6699 Ops/s | |
test_populate_rb[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] | 0.1474s | 29.7935ms | 33.5644 Ops/s | 36.6506 Ops/s | |
test_populate_rb[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] | 0.1447s | 26.9986ms | 37.0390 Ops/s | 33.9626 Ops/s | |
test_populate_rb[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] | 0.1386s | 29.0161ms | 34.4637 Ops/s | 37.0771 Ops/s | |
test_populate_rb[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] | 0.1351s | 28.7294ms | 34.8076 Ops/s | 33.9527 Ops/s | |
test_populate_rb[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] | 0.1352s | 26.3812ms | 37.9058 Ops/s | 37.8172 Ops/s | |
test_populate_rb[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] | 0.1366s | 29.4973ms | 33.9014 Ops/s | 34.4095 Ops/s | |
test_populate_rb[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] | 0.1359s | 26.3565ms | 37.9413 Ops/s | 34.1369 Ops/s |
albertbou92
pushed a commit
to PyTorchRL/rl
that referenced
this pull request
Sep 18, 2023
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
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Tests
Incomplete or broken unit tests
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
depends on pytorch/tensordict#528