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 Exclude / Double2Float transforms #2101

Merged
merged 2 commits into from
Apr 23, 2024
Merged

[BugFix] Fix Exclude / Double2Float transforms #2101

merged 2 commits into from
Apr 23, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Apr 23, 2024

No description provided.

Copy link

pytorch-bot bot commented Apr 23, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2101

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

❌ 13 New Failures

As of commit 4982cba with merge base bfadce9 (image):

NEW FAILURES - The following jobs have failed:

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 Apr 23, 2024
@vmoens vmoens added the bug Something isn't working label Apr 23, 2024
@vmoens vmoens changed the title [BugFix] Random fixes [BugFix] Fix Exclude / Double2Float transforms Apr 23, 2024
Copy link

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 52.7494ms 52.1480ms 19.1762 Ops/s 18.3648 Ops/s $\color{#35bf28}+4.42\%$
test_sync 45.3188ms 29.6852ms 33.6868 Ops/s 31.9775 Ops/s $\textbf{\color{#35bf28}+5.35\%}$
test_async 47.6044ms 26.5884ms 37.6104 Ops/s 36.7394 Ops/s $\color{#35bf28}+2.37\%$
test_simple 0.3878s 0.3370s 2.9670 Ops/s 3.0698 Ops/s $\color{#d91a1a}-3.35\%$
test_transformed 0.5246s 0.4800s 2.0832 Ops/s 2.0939 Ops/s $\color{#d91a1a}-0.51\%$
test_serial 1.2110s 1.1694s 0.8551 Ops/s 0.8503 Ops/s $\color{#35bf28}+0.56\%$
test_parallel 1.0357s 1.0000s 1.0000 Ops/s 1.0053 Ops/s $\color{#d91a1a}-0.52\%$
test_step_mdp_speed[True-True-True-True-True] 0.1200ms 21.3118μs 46.9223 KOps/s 47.8235 KOps/s $\color{#d91a1a}-1.88\%$
test_step_mdp_speed[True-True-True-True-False] 40.5160μs 12.9361μs 77.3033 KOps/s 78.0046 KOps/s $\color{#d91a1a}-0.90\%$
test_step_mdp_speed[True-True-True-False-True] 35.7560μs 12.4982μs 80.0116 KOps/s 80.5989 KOps/s $\color{#d91a1a}-0.73\%$
test_step_mdp_speed[True-True-True-False-False] 28.8240μs 7.5862μs 131.8189 KOps/s 132.9701 KOps/s $\color{#d91a1a}-0.87\%$
test_step_mdp_speed[True-True-False-True-True] 49.7630μs 22.7571μs 43.9423 KOps/s 44.3385 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[True-True-False-True-False] 66.3550μs 14.2394μs 70.2276 KOps/s 70.4982 KOps/s $\color{#d91a1a}-0.38\%$
test_step_mdp_speed[True-True-False-False-True] 43.1410μs 13.7185μs 72.8942 KOps/s 72.7771 KOps/s $\color{#35bf28}+0.16\%$
test_step_mdp_speed[True-True-False-False-False] 33.1930μs 8.7565μs 114.2009 KOps/s 112.6974 KOps/s $\color{#35bf28}+1.33\%$
test_step_mdp_speed[True-False-True-True-True] 63.3490μs 24.1217μs 41.4565 KOps/s 41.9972 KOps/s $\color{#d91a1a}-1.29\%$
test_step_mdp_speed[True-False-True-True-False] 37.8230μs 15.5818μs 64.1775 KOps/s 64.0948 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[True-False-True-False-True] 57.6310μs 13.6344μs 73.3441 KOps/s 73.3543 KOps/s $\color{#d91a1a}-0.01\%$
test_step_mdp_speed[True-False-True-False-False] 27.8940μs 8.7840μs 113.8428 KOps/s 112.8018 KOps/s $\color{#35bf28}+0.92\%$
test_step_mdp_speed[True-False-False-True-True] 72.1700μs 24.7855μs 40.3462 KOps/s 40.0877 KOps/s $\color{#35bf28}+0.64\%$
test_step_mdp_speed[True-False-False-True-False] 43.2210μs 16.7476μs 59.7099 KOps/s 60.1507 KOps/s $\color{#d91a1a}-0.73\%$
test_step_mdp_speed[True-False-False-False-True] 42.6700μs 14.9022μs 67.1043 KOps/s 65.2513 KOps/s $\color{#35bf28}+2.84\%$
test_step_mdp_speed[True-False-False-False-False] 33.2020μs 10.0375μs 99.6264 KOps/s 100.0677 KOps/s $\color{#d91a1a}-0.44\%$
test_step_mdp_speed[False-True-True-True-True] 0.3011ms 25.0266μs 39.9575 KOps/s 42.0302 KOps/s $\color{#d91a1a}-4.93\%$
test_step_mdp_speed[False-True-True-True-False] 53.2900μs 15.5041μs 64.4992 KOps/s 64.5974 KOps/s $\color{#d91a1a}-0.15\%$
test_step_mdp_speed[False-True-True-False-True] 39.2730μs 15.7765μs 63.3855 KOps/s 63.2085 KOps/s $\color{#35bf28}+0.28\%$
test_step_mdp_speed[False-True-True-False-False] 35.4570μs 9.9233μs 100.7728 KOps/s 100.3839 KOps/s $\color{#35bf28}+0.39\%$
test_step_mdp_speed[False-True-False-True-True] 45.4650μs 25.2687μs 39.5747 KOps/s 39.7617 KOps/s $\color{#d91a1a}-0.47\%$
test_step_mdp_speed[False-True-False-True-False] 74.1590μs 16.6294μs 60.1344 KOps/s 60.5860 KOps/s $\color{#d91a1a}-0.75\%$
test_step_mdp_speed[False-True-False-False-True] 45.6960μs 17.0106μs 58.7867 KOps/s 59.3049 KOps/s $\color{#d91a1a}-0.87\%$
test_step_mdp_speed[False-True-False-False-False] 0.1544ms 11.3188μs 88.3483 KOps/s 90.0315 KOps/s $\color{#d91a1a}-1.87\%$
test_step_mdp_speed[False-False-True-True-True] 59.3720μs 26.3499μs 37.9508 KOps/s 38.3012 KOps/s $\color{#d91a1a}-0.91\%$
test_step_mdp_speed[False-False-True-True-False] 54.3830μs 17.9777μs 55.6244 KOps/s 56.2849 KOps/s $\color{#d91a1a}-1.17\%$
test_step_mdp_speed[False-False-True-False-True] 46.1270μs 17.0478μs 58.6586 KOps/s 59.5920 KOps/s $\color{#d91a1a}-1.57\%$
test_step_mdp_speed[False-False-True-False-False] 35.2870μs 11.1855μs 89.4018 KOps/s 89.4150 KOps/s $\color{#d91a1a}-0.01\%$
test_step_mdp_speed[False-False-False-True-True] 81.4630μs 27.2917μs 36.6411 KOps/s 37.1654 KOps/s $\color{#d91a1a}-1.41\%$
test_step_mdp_speed[False-False-False-True-False] 76.2530μs 19.0186μs 52.5802 KOps/s 53.5858 KOps/s $\color{#d91a1a}-1.88\%$
test_step_mdp_speed[False-False-False-False-True] 46.7080μs 18.0302μs 55.4626 KOps/s 55.7212 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[False-False-False-False-False] 62.5680μs 12.2431μs 81.6790 KOps/s 82.1513 KOps/s $\color{#d91a1a}-0.57\%$
test_values[generalized_advantage_estimate-True-True] 12.0655ms 9.3275ms 107.2100 Ops/s 103.5871 Ops/s $\color{#35bf28}+3.50\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.7768ms 35.3656ms 28.2761 Ops/s 30.3829 Ops/s $\textbf{\color{#d91a1a}-6.93\%}$
test_values[td0_return_estimate-False-False] 0.2196ms 0.1636ms 6.1139 KOps/s 6.0405 KOps/s $\color{#35bf28}+1.21\%$
test_values[td1_return_estimate-False-False] 23.1453ms 22.7215ms 44.0112 Ops/s 42.5273 Ops/s $\color{#35bf28}+3.49\%$
test_values[vec_td1_return_estimate-False-False] 36.7109ms 35.4198ms 28.2328 Ops/s 30.3353 Ops/s $\textbf{\color{#d91a1a}-6.93\%}$
test_values[td_lambda_return_estimate-True-False] 34.9513ms 32.7583ms 30.5266 Ops/s 29.6769 Ops/s $\color{#35bf28}+2.86\%$
test_values[vec_td_lambda_return_estimate-True-False] 36.3217ms 35.3816ms 28.2633 Ops/s 30.3683 Ops/s $\textbf{\color{#d91a1a}-6.93\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.1724ms 8.0351ms 124.4538 Ops/s 118.6290 Ops/s $\color{#35bf28}+4.91\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.1537ms 1.8459ms 541.7431 Ops/s 507.6719 Ops/s $\textbf{\color{#35bf28}+6.71\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4551ms 0.3447ms 2.9012 KOps/s 2.8719 KOps/s $\color{#35bf28}+1.02\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 47.5983ms 45.6796ms 21.8916 Ops/s 24.9242 Ops/s $\textbf{\color{#d91a1a}-12.17\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.6249ms 3.0090ms 332.3391 Ops/s 330.9057 Ops/s $\color{#35bf28}+0.43\%$
test_dqn_speed 7.5972ms 1.3422ms 745.0642 Ops/s 737.9212 Ops/s $\color{#35bf28}+0.97\%$
test_ddpg_speed 2.8479ms 2.6409ms 378.6576 Ops/s 378.1533 Ops/s $\color{#35bf28}+0.13\%$
test_sac_speed 9.8375ms 8.1185ms 123.1748 Ops/s 122.4541 Ops/s $\color{#35bf28}+0.59\%$
test_redq_speed 88.8930ms 13.7892ms 72.5203 Ops/s 77.3220 Ops/s $\textbf{\color{#d91a1a}-6.21\%}$
test_redq_deprec_speed 14.4843ms 12.8113ms 78.0559 Ops/s 78.5352 Ops/s $\color{#d91a1a}-0.61\%$
test_td3_speed 10.7511ms 8.0192ms 124.7013 Ops/s 124.7199 Ops/s $\color{#d91a1a}-0.01\%$
test_cql_speed 36.4740ms 35.6916ms 28.0178 Ops/s 27.9072 Ops/s $\color{#35bf28}+0.40\%$
test_a2c_speed 8.3512ms 7.2810ms 137.3430 Ops/s 137.3459 Ops/s $-0.00\%$
test_ppo_speed 8.6695ms 7.5757ms 132.0008 Ops/s 133.5103 Ops/s $\color{#d91a1a}-1.13\%$
test_reinforce_speed 7.5142ms 6.5008ms 153.8261 Ops/s 153.8797 Ops/s $\color{#d91a1a}-0.03\%$
test_iql_speed 33.6329ms 31.9840ms 31.2656 Ops/s 31.1135 Ops/s $\color{#35bf28}+0.49\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.3254ms 2.0120ms 497.0284 Ops/s 494.3422 Ops/s $\color{#35bf28}+0.54\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6480ms 0.4910ms 2.0365 KOps/s 2.0168 KOps/s $\color{#35bf28}+0.98\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 3.6167ms 0.4698ms 2.1288 KOps/s 2.1358 KOps/s $\color{#d91a1a}-0.33\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.9836ms 2.0262ms 493.5261 Ops/s 501.6414 Ops/s $\color{#d91a1a}-1.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9239ms 0.5008ms 1.9966 KOps/s 2.0523 KOps/s $\color{#d91a1a}-2.71\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6042ms 0.4589ms 2.1791 KOps/s 2.1526 KOps/s $\color{#35bf28}+1.23\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.9052ms 1.2048ms 830.0157 Ops/s 823.9982 Ops/s $\color{#35bf28}+0.73\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5559ms 1.1321ms 883.3527 Ops/s 872.6925 Ops/s $\color{#35bf28}+1.22\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.4675ms 2.1888ms 456.8666 Ops/s 471.4202 Ops/s $\color{#d91a1a}-3.09\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8565ms 0.6058ms 1.6506 KOps/s 1.6427 KOps/s $\color{#35bf28}+0.48\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 3.6495ms 0.5827ms 1.7162 KOps/s 1.7139 KOps/s $\color{#35bf28}+0.13\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.9312ms 2.0977ms 476.7127 Ops/s 500.6540 Ops/s $\color{#d91a1a}-4.78\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7959ms 0.4981ms 2.0077 KOps/s 2.0160 KOps/s $\color{#d91a1a}-0.41\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 3.7262ms 0.4763ms 2.0993 KOps/s 2.1048 KOps/s $\color{#d91a1a}-0.26\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.7208ms 2.0330ms 491.8748 Ops/s 495.4225 Ops/s $\color{#d91a1a}-0.72\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8177ms 0.4888ms 2.0460 KOps/s 2.0537 KOps/s $\color{#d91a1a}-0.38\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6586ms 0.4618ms 2.1655 KOps/s 2.1161 KOps/s $\color{#35bf28}+2.33\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.3545ms 2.1625ms 462.4333 Ops/s 474.5296 Ops/s $\color{#d91a1a}-2.55\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3202ms 0.6133ms 1.6306 KOps/s 1.6379 KOps/s $\color{#d91a1a}-0.44\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9114ms 0.5838ms 1.7128 KOps/s 1.7147 KOps/s $\color{#d91a1a}-0.11\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1076s 7.4897ms 133.5175 Ops/s 134.0120 Ops/s $\color{#d91a1a}-0.37\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 13.9399ms 11.7445ms 85.1461 Ops/s 83.2834 Ops/s $\color{#35bf28}+2.24\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.7735ms 1.0493ms 953.0214 Ops/s 929.8185 Ops/s $\color{#35bf28}+2.50\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 98.5324ms 5.4908ms 182.1241 Ops/s 180.3393 Ops/s $\color{#35bf28}+0.99\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 13.9464ms 11.7377ms 85.1956 Ops/s 83.9955 Ops/s $\color{#35bf28}+1.43\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.7362ms 1.0597ms 943.6339 Ops/s 929.6621 Ops/s $\color{#35bf28}+1.50\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 99.3238ms 7.6226ms 131.1884 Ops/s 128.6679 Ops/s $\color{#35bf28}+1.96\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 14.8931ms 12.0803ms 82.7795 Ops/s 81.6472 Ops/s $\color{#35bf28}+1.39\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 1.9845ms 1.3259ms 754.2184 Ops/s 712.5795 Ops/s $\textbf{\color{#35bf28}+5.84\%}$

Copy link

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}2$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1001s 99.9663ms 10.0034 Ops/s 9.3962 Ops/s $\textbf{\color{#35bf28}+6.46\%}$
test_sync 91.5771ms 88.7729ms 11.2647 Ops/s 11.4034 Ops/s $\color{#d91a1a}-1.22\%$
test_async 0.1599s 71.8238ms 13.9230 Ops/s 14.3135 Ops/s $\color{#d91a1a}-2.73\%$
test_single_pixels 0.1101s 0.1098s 9.1098 Ops/s 8.9669 Ops/s $\color{#35bf28}+1.59\%$
test_sync_pixels 77.3060ms 71.4002ms 14.0056 Ops/s 15.1815 Ops/s $\textbf{\color{#d91a1a}-7.75\%}$
test_async_pixels 81.8740ms 64.1632ms 15.5853 Ops/s 16.0235 Ops/s $\color{#d91a1a}-2.74\%$
test_simple 0.7416s 0.6882s 1.4530 Ops/s 1.4337 Ops/s $\color{#35bf28}+1.35\%$
test_transformed 0.9599s 0.9066s 1.1031 Ops/s 1.0808 Ops/s $\color{#35bf28}+2.06\%$
test_serial 2.1326s 2.1048s 0.4751 Ops/s 0.4732 Ops/s $\color{#35bf28}+0.40\%$
test_parallel 1.7755s 1.7356s 0.5762 Ops/s 0.5532 Ops/s $\color{#35bf28}+4.16\%$
test_step_mdp_speed[True-True-True-True-True] 0.1608ms 32.3574μs 30.9048 KOps/s 31.4712 KOps/s $\color{#d91a1a}-1.80\%$
test_step_mdp_speed[True-True-True-True-False] 36.8910μs 19.9509μs 50.1230 KOps/s 52.5300 KOps/s $\color{#d91a1a}-4.58\%$
test_step_mdp_speed[True-True-True-False-True] 50.3210μs 18.8172μs 53.1429 KOps/s 55.2868 KOps/s $\color{#d91a1a}-3.88\%$
test_step_mdp_speed[True-True-True-False-False] 81.8810μs 11.0496μs 90.5012 KOps/s 91.3181 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[True-True-False-True-True] 58.2800μs 34.9439μs 28.6173 KOps/s 29.5134 KOps/s $\color{#d91a1a}-3.04\%$
test_step_mdp_speed[True-True-False-True-False] 45.3710μs 21.5932μs 46.3108 KOps/s 46.9312 KOps/s $\color{#d91a1a}-1.32\%$
test_step_mdp_speed[True-True-False-False-True] 40.1300μs 20.4150μs 48.9837 KOps/s 49.0826 KOps/s $\color{#d91a1a}-0.20\%$
test_step_mdp_speed[True-True-False-False-False] 32.7600μs 13.1594μs 75.9915 KOps/s 78.0065 KOps/s $\color{#d91a1a}-2.58\%$
test_step_mdp_speed[True-False-True-True-True] 74.4010μs 36.2219μs 27.6076 KOps/s 27.7252 KOps/s $\color{#d91a1a}-0.42\%$
test_step_mdp_speed[True-False-True-True-False] 41.9310μs 23.4623μs 42.6216 KOps/s 43.2512 KOps/s $\color{#d91a1a}-1.46\%$
test_step_mdp_speed[True-False-True-False-True] 45.2510μs 20.4801μs 48.8279 KOps/s 50.4076 KOps/s $\color{#d91a1a}-3.13\%$
test_step_mdp_speed[True-False-True-False-False] 32.3610μs 13.2080μs 75.7119 KOps/s 77.7713 KOps/s $\color{#d91a1a}-2.65\%$
test_step_mdp_speed[True-False-False-True-True] 57.8510μs 38.4882μs 25.9820 KOps/s 26.7595 KOps/s $\color{#d91a1a}-2.91\%$
test_step_mdp_speed[True-False-False-True-False] 45.0810μs 25.3893μs 39.3866 KOps/s 39.9463 KOps/s $\color{#d91a1a}-1.40\%$
test_step_mdp_speed[True-False-False-False-True] 37.9700μs 22.3110μs 44.8210 KOps/s 46.1936 KOps/s $\color{#d91a1a}-2.97\%$
test_step_mdp_speed[True-False-False-False-False] 34.5310μs 14.8512μs 67.3344 KOps/s 68.3630 KOps/s $\color{#d91a1a}-1.50\%$
test_step_mdp_speed[False-True-True-True-True] 64.3810μs 36.3628μs 27.5007 KOps/s 27.9339 KOps/s $\color{#d91a1a}-1.55\%$
test_step_mdp_speed[False-True-True-True-False] 42.6710μs 23.3026μs 42.9136 KOps/s 43.1755 KOps/s $\color{#d91a1a}-0.61\%$
test_step_mdp_speed[False-True-True-False-True] 86.5300μs 24.3088μs 41.1375 KOps/s 42.2267 KOps/s $\color{#d91a1a}-2.58\%$
test_step_mdp_speed[False-True-True-False-False] 36.7200μs 15.0227μs 66.5659 KOps/s 68.2235 KOps/s $\color{#d91a1a}-2.43\%$
test_step_mdp_speed[False-True-False-True-True] 61.3810μs 39.4440μs 25.3524 KOps/s 26.1469 KOps/s $\color{#d91a1a}-3.04\%$
test_step_mdp_speed[False-True-False-True-False] 53.1400μs 25.6461μs 38.9923 KOps/s 40.1515 KOps/s $\color{#d91a1a}-2.89\%$
test_step_mdp_speed[False-True-False-False-True] 53.3310μs 26.1707μs 38.2107 KOps/s 39.0714 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[False-True-False-False-False] 34.9310μs 16.6944μs 59.9004 KOps/s 61.2883 KOps/s $\color{#d91a1a}-2.26\%$
test_step_mdp_speed[False-False-True-True-True] 66.3720μs 40.0587μs 24.9634 KOps/s 25.1101 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[False-False-True-True-False] 48.1810μs 27.1163μs 36.8782 KOps/s 37.2397 KOps/s $\color{#d91a1a}-0.97\%$
test_step_mdp_speed[False-False-True-False-True] 51.2500μs 26.3469μs 37.9551 KOps/s 39.0010 KOps/s $\color{#d91a1a}-2.68\%$
test_step_mdp_speed[False-False-True-False-False] 64.1900μs 16.6773μs 59.9617 KOps/s 60.7710 KOps/s $\color{#d91a1a}-1.33\%$
test_step_mdp_speed[False-False-False-True-True] 67.0800μs 41.6471μs 24.0113 KOps/s 24.4341 KOps/s $\color{#d91a1a}-1.73\%$
test_step_mdp_speed[False-False-False-True-False] 60.2910μs 28.8597μs 34.6504 KOps/s 35.0662 KOps/s $\color{#d91a1a}-1.19\%$
test_step_mdp_speed[False-False-False-False-True] 44.8510μs 27.3564μs 36.5546 KOps/s 37.4088 KOps/s $\color{#d91a1a}-2.28\%$
test_step_mdp_speed[False-False-False-False-False] 38.7000μs 18.6575μs 53.5979 KOps/s 55.2281 KOps/s $\color{#d91a1a}-2.95\%$
test_values[generalized_advantage_estimate-True-True] 26.2960ms 25.6834ms 38.9356 Ops/s 40.8467 Ops/s $\color{#d91a1a}-4.68\%$
test_values[vec_generalized_advantage_estimate-True-True] 83.0720ms 3.2267ms 309.9111 Ops/s 310.7837 Ops/s $\color{#d91a1a}-0.28\%$
test_values[td0_return_estimate-False-False] 95.3210μs 67.6192μs 14.7887 KOps/s 15.5597 KOps/s $\color{#d91a1a}-4.96\%$
test_values[td1_return_estimate-False-False] 54.9189ms 52.6549ms 18.9916 Ops/s 19.2989 Ops/s $\color{#d91a1a}-1.59\%$
test_values[vec_td1_return_estimate-False-False] 2.1432ms 1.7615ms 567.7053 Ops/s 567.0747 Ops/s $\color{#35bf28}+0.11\%$
test_values[td_lambda_return_estimate-True-False] 86.6995ms 84.5206ms 11.8314 Ops/s 12.0601 Ops/s $\color{#d91a1a}-1.90\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.1159ms 1.7558ms 569.5555 Ops/s 567.5979 Ops/s $\color{#35bf28}+0.34\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.5490ms 23.4122ms 42.7127 Ops/s 43.2008 Ops/s $\color{#d91a1a}-1.13\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9089ms 0.6956ms 1.4377 KOps/s 1.4369 KOps/s $\color{#35bf28}+0.05\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7139ms 0.6485ms 1.5420 KOps/s 1.5452 KOps/s $\color{#d91a1a}-0.21\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5500ms 1.4528ms 688.3331 Ops/s 690.4438 Ops/s $\color{#d91a1a}-0.31\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9441ms 0.6699ms 1.4928 KOps/s 1.4914 KOps/s $\color{#35bf28}+0.10\%$
test_dqn_speed 7.9305ms 1.4448ms 692.1136 Ops/s 666.3835 Ops/s $\color{#35bf28}+3.86\%$
test_ddpg_speed 2.9886ms 2.6936ms 371.2439 Ops/s 360.9844 Ops/s $\color{#35bf28}+2.84\%$
test_sac_speed 8.6827ms 8.0413ms 124.3574 Ops/s 111.5849 Ops/s $\textbf{\color{#35bf28}+11.45\%}$
test_redq_speed 10.9304ms 10.0706ms 99.2988 Ops/s 97.7871 Ops/s $\color{#35bf28}+1.55\%$
test_redq_deprec_speed 11.3821ms 10.9460ms 91.3576 Ops/s 88.1074 Ops/s $\color{#35bf28}+3.69\%$
test_td3_speed 8.1784ms 7.9874ms 125.1968 Ops/s 124.5324 Ops/s $\color{#35bf28}+0.53\%$
test_cql_speed 25.9792ms 24.8845ms 40.1857 Ops/s 39.3331 Ops/s $\color{#35bf28}+2.17\%$
test_a2c_speed 5.7019ms 5.4796ms 182.4942 Ops/s 175.6436 Ops/s $\color{#35bf28}+3.90\%$
test_ppo_speed 6.4074ms 5.7928ms 172.6288 Ops/s 166.9950 Ops/s $\color{#35bf28}+3.37\%$
test_reinforce_speed 4.7464ms 4.5152ms 221.4727 Ops/s 219.4052 Ops/s $\color{#35bf28}+0.94\%$
test_iql_speed 19.6341ms 19.1564ms 52.2019 Ops/s 51.4852 Ops/s $\color{#35bf28}+1.39\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.8639ms 2.7368ms 365.3841 Ops/s 359.6560 Ops/s $\color{#35bf28}+1.59\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.4345ms 0.5328ms 1.8769 KOps/s 1.8585 KOps/s $\color{#35bf28}+0.99\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6740ms 0.5102ms 1.9599 KOps/s 1.9581 KOps/s $\color{#35bf28}+0.09\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9239ms 2.7459ms 364.1828 Ops/s 356.6024 Ops/s $\color{#35bf28}+2.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6524ms 0.5257ms 1.9022 KOps/s 1.8911 KOps/s $\color{#35bf28}+0.59\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.2184ms 0.5063ms 1.9751 KOps/s 1.9692 KOps/s $\color{#35bf28}+0.30\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.5243ms 1.4029ms 712.8194 Ops/s 703.6576 Ops/s $\color{#35bf28}+1.30\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4731ms 1.3375ms 747.6772 Ops/s 746.3869 Ops/s $\color{#35bf28}+0.17\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.9818ms 2.8541ms 350.3721 Ops/s 344.8133 Ops/s $\color{#35bf28}+1.61\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2930ms 0.6533ms 1.5307 KOps/s 1.5162 KOps/s $\color{#35bf28}+0.95\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7579ms 0.6294ms 1.5888 KOps/s 1.5747 KOps/s $\color{#35bf28}+0.89\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.8285ms 2.7150ms 368.3229 Ops/s 359.1071 Ops/s $\color{#35bf28}+2.57\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1466ms 0.5376ms 1.8601 KOps/s 1.8679 KOps/s $\color{#d91a1a}-0.42\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6754ms 0.5133ms 1.9481 KOps/s 1.9463 KOps/s $\color{#35bf28}+0.10\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9384ms 2.7422ms 364.6661 Ops/s 357.5369 Ops/s $\color{#35bf28}+1.99\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6315ms 0.5276ms 1.8954 KOps/s 1.8884 KOps/s $\color{#35bf28}+0.37\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7072ms 0.5056ms 1.9778 KOps/s 1.9741 KOps/s $\color{#35bf28}+0.19\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.9230ms 2.8463ms 351.3281 Ops/s 342.8043 Ops/s $\color{#35bf28}+2.49\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3640ms 0.6529ms 1.5315 KOps/s 1.5113 KOps/s $\color{#35bf28}+1.34\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7408ms 0.6266ms 1.5959 KOps/s 1.5734 KOps/s $\color{#35bf28}+1.43\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1244s 9.3927ms 106.4657 Ops/s 103.9130 Ops/s $\color{#35bf28}+2.46\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.3601ms 14.2818ms 70.0194 Ops/s 69.3000 Ops/s $\color{#35bf28}+1.04\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.0986ms 1.2984ms 770.2064 Ops/s 771.4670 Ops/s $\color{#d91a1a}-0.16\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1154s 7.0099ms 142.6558 Ops/s 140.6127 Ops/s $\color{#35bf28}+1.45\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.8136ms 14.4956ms 68.9864 Ops/s 69.4478 Ops/s $\color{#d91a1a}-0.66\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.6403ms 1.2796ms 781.4645 Ops/s 774.8131 Ops/s $\color{#35bf28}+0.86\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1161s 9.6175ms 103.9769 Ops/s 133.0409 Ops/s $\textbf{\color{#d91a1a}-21.85\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 16.9925ms 14.9910ms 66.7065 Ops/s 67.2326 Ops/s $\color{#d91a1a}-0.78\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.5404ms 1.4833ms 674.1553 Ops/s 654.0434 Ops/s $\color{#35bf28}+3.08\%$

@vmoens vmoens merged commit 7dd0128 into main Apr 23, 2024
54 of 67 checks passed
@vmoens vmoens deleted the fix-dreamer branch April 23, 2024 15:22
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.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants