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

[Feature] Add support for Unity MLAgents environments #2161

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented May 16, 2024

No description provided.

Copy link

pytorch-bot bot commented May 16, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2161

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

❌ 7 New Failures, 4 Unrelated Failures

As of commit 649b625 with merge base 259f20d (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.

@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 May 16, 2024
Copy link

github-actions bot commented May 16, 2024

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}13$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 56.2924ms 55.6063ms 17.9836 Ops/s 18.4690 Ops/s $\color{#d91a1a}-2.63\%$
test_sync 40.5090ms 30.3089ms 32.9936 Ops/s 33.4801 Ops/s $\color{#d91a1a}-1.45\%$
test_async 54.8688ms 27.0534ms 36.9640 Ops/s 34.6567 Ops/s $\textbf{\color{#35bf28}+6.66\%}$
test_simple 0.4142s 0.3579s 2.7944 Ops/s 2.9786 Ops/s $\textbf{\color{#d91a1a}-6.18\%}$
test_transformed 0.5046s 0.5010s 1.9960 Ops/s 2.0817 Ops/s $\color{#d91a1a}-4.12\%$
test_serial 1.3226s 1.2571s 0.7955 Ops/s 0.8216 Ops/s $\color{#d91a1a}-3.17\%$
test_parallel 1.0744s 1.0237s 0.9768 Ops/s 0.9932 Ops/s $\color{#d91a1a}-1.65\%$
test_step_mdp_speed[True-True-True-True-True] 0.2066ms 21.6232μs 46.2466 KOps/s 47.6456 KOps/s $\color{#d91a1a}-2.94\%$
test_step_mdp_speed[True-True-True-True-False] 41.4170μs 13.0833μs 76.4334 KOps/s 77.7200 KOps/s $\color{#d91a1a}-1.66\%$
test_step_mdp_speed[True-True-True-False-True] 37.4800μs 12.7310μs 78.5484 KOps/s 80.6479 KOps/s $\color{#d91a1a}-2.60\%$
test_step_mdp_speed[True-True-True-False-False] 34.1540μs 7.7905μs 128.3623 KOps/s 125.2160 KOps/s $\color{#35bf28}+2.51\%$
test_step_mdp_speed[True-True-False-True-True] 78.1060μs 23.0683μs 43.3496 KOps/s 45.0295 KOps/s $\color{#d91a1a}-3.73\%$
test_step_mdp_speed[True-True-False-True-False] 48.5610μs 14.3988μs 69.4501 KOps/s 71.7019 KOps/s $\color{#d91a1a}-3.14\%$
test_step_mdp_speed[True-True-False-False-True] 43.8420μs 13.9235μs 71.8211 KOps/s 75.3363 KOps/s $\color{#d91a1a}-4.67\%$
test_step_mdp_speed[True-True-False-False-False] 37.9710μs 8.9222μs 112.0794 KOps/s 114.9219 KOps/s $\color{#d91a1a}-2.47\%$
test_step_mdp_speed[True-False-True-True-True] 67.5970μs 24.4062μs 40.9732 KOps/s 42.0078 KOps/s $\color{#d91a1a}-2.46\%$
test_step_mdp_speed[True-False-True-True-False] 0.1314ms 17.2483μs 57.9769 KOps/s 65.1313 KOps/s $\textbf{\color{#d91a1a}-10.98\%}$
test_step_mdp_speed[True-False-True-False-True] 41.3670μs 14.0851μs 70.9972 KOps/s 74.5090 KOps/s $\color{#d91a1a}-4.71\%$
test_step_mdp_speed[True-False-True-False-False] 26.4400μs 8.9779μs 111.3849 KOps/s 113.0009 KOps/s $\color{#d91a1a}-1.43\%$
test_step_mdp_speed[True-False-False-True-True] 74.3890μs 25.6606μs 38.9702 KOps/s 40.1104 KOps/s $\color{#d91a1a}-2.84\%$
test_step_mdp_speed[True-False-False-True-False] 37.9210μs 16.9966μs 58.8355 KOps/s 60.8927 KOps/s $\color{#d91a1a}-3.38\%$
test_step_mdp_speed[True-False-False-False-True] 42.5190μs 15.0420μs 66.4806 KOps/s 69.3650 KOps/s $\color{#d91a1a}-4.16\%$
test_step_mdp_speed[True-False-False-False-False] 47.5790μs 10.2252μs 97.7975 KOps/s 101.9943 KOps/s $\color{#d91a1a}-4.11\%$
test_step_mdp_speed[False-True-True-True-True] 92.2330μs 24.2523μs 41.2331 KOps/s 42.4192 KOps/s $\color{#d91a1a}-2.80\%$
test_step_mdp_speed[False-True-True-True-False] 0.1525ms 15.9954μs 62.5179 KOps/s 65.2779 KOps/s $\color{#d91a1a}-4.23\%$
test_step_mdp_speed[False-True-True-False-True] 64.6710μs 16.0439μs 62.3289 KOps/s 64.0897 KOps/s $\color{#d91a1a}-2.75\%$
test_step_mdp_speed[False-True-True-False-False] 46.3860μs 10.2117μs 97.9272 KOps/s 101.4962 KOps/s $\color{#d91a1a}-3.52\%$
test_step_mdp_speed[False-True-False-True-True] 63.4390μs 26.3773μs 37.9115 KOps/s 40.6046 KOps/s $\textbf{\color{#d91a1a}-6.63\%}$
test_step_mdp_speed[False-True-False-True-False] 68.2570μs 16.7566μs 59.6781 KOps/s 60.5512 KOps/s $\color{#d91a1a}-1.44\%$
test_step_mdp_speed[False-True-False-False-True] 0.1070ms 17.5733μs 56.9046 KOps/s 59.9052 KOps/s $\textbf{\color{#d91a1a}-5.01\%}$
test_step_mdp_speed[False-True-False-False-False] 56.7160μs 11.4053μs 87.6785 KOps/s 90.6804 KOps/s $\color{#d91a1a}-3.31\%$
test_step_mdp_speed[False-False-True-True-True] 0.2147ms 26.9795μs 37.0652 KOps/s 38.5535 KOps/s $\color{#d91a1a}-3.86\%$
test_step_mdp_speed[False-False-True-True-False] 70.1820μs 18.1125μs 55.2105 KOps/s 56.5802 KOps/s $\color{#d91a1a}-2.42\%$
test_step_mdp_speed[False-False-True-False-True] 45.8260μs 17.5301μs 57.0449 KOps/s 59.5445 KOps/s $\color{#d91a1a}-4.20\%$
test_step_mdp_speed[False-False-True-False-False] 54.8530μs 11.5054μs 86.9154 KOps/s 91.3897 KOps/s $\color{#d91a1a}-4.90\%$
test_step_mdp_speed[False-False-False-True-True] 49.1420μs 28.4689μs 35.1261 KOps/s 36.4225 KOps/s $\color{#d91a1a}-3.56\%$
test_step_mdp_speed[False-False-False-True-False] 54.2320μs 19.3182μs 51.7647 KOps/s 53.2256 KOps/s $\color{#d91a1a}-2.74\%$
test_step_mdp_speed[False-False-False-False-True] 44.4740μs 18.3840μs 54.3952 KOps/s 56.1592 KOps/s $\color{#d91a1a}-3.14\%$
test_step_mdp_speed[False-False-False-False-False] 75.0810μs 12.4600μs 80.2570 KOps/s 82.8572 KOps/s $\color{#d91a1a}-3.14\%$
test_values[generalized_advantage_estimate-True-True] 9.5368ms 9.2172ms 108.4930 Ops/s 103.9146 Ops/s $\color{#35bf28}+4.41\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.9630ms 35.8065ms 27.9279 Ops/s 27.7017 Ops/s $\color{#35bf28}+0.82\%$
test_values[td0_return_estimate-False-False] 0.2292ms 0.1875ms 5.3347 KOps/s 5.6478 KOps/s $\textbf{\color{#d91a1a}-5.54\%}$
test_values[td1_return_estimate-False-False] 27.0553ms 23.6891ms 42.2135 Ops/s 41.0537 Ops/s $\color{#35bf28}+2.83\%$
test_values[vec_td1_return_estimate-False-False] 37.0775ms 35.9105ms 27.8470 Ops/s 27.2930 Ops/s $\color{#35bf28}+2.03\%$
test_values[td_lambda_return_estimate-True-False] 36.8226ms 33.6773ms 29.6936 Ops/s 28.7309 Ops/s $\color{#35bf28}+3.35\%$
test_values[vec_td_lambda_return_estimate-True-False] 38.8233ms 36.4530ms 27.4326 Ops/s 27.5270 Ops/s $\color{#d91a1a}-0.34\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.3303ms 8.1951ms 122.0248 Ops/s 116.9661 Ops/s $\color{#35bf28}+4.32\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.5253ms 2.0371ms 490.8988 Ops/s 496.9327 Ops/s $\color{#d91a1a}-1.21\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4295ms 0.3513ms 2.8465 KOps/s 2.8251 KOps/s $\color{#35bf28}+0.76\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 46.6802ms 45.8159ms 21.8265 Ops/s 20.9650 Ops/s $\color{#35bf28}+4.11\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.7334ms 3.0327ms 329.7441 Ops/s 330.8875 Ops/s $\color{#d91a1a}-0.35\%$
test_dqn_speed 1.6362ms 1.3964ms 716.1110 Ops/s 722.0315 Ops/s $\color{#d91a1a}-0.82\%$
test_ddpg_speed 3.4956ms 2.9431ms 339.7791 Ops/s 348.3684 Ops/s $\color{#d91a1a}-2.47\%$
test_sac_speed 10.7098ms 8.7486ms 114.3038 Ops/s 105.6378 Ops/s $\textbf{\color{#35bf28}+8.20\%}$
test_redq_speed 17.2647ms 13.6736ms 73.1335 Ops/s 75.1475 Ops/s $\color{#d91a1a}-2.68\%$
test_redq_deprec_speed 16.0460ms 13.7700ms 72.6214 Ops/s 75.7047 Ops/s $\color{#d91a1a}-4.07\%$
test_td3_speed 17.0463ms 8.6748ms 115.2765 Ops/s 116.6007 Ops/s $\color{#d91a1a}-1.14\%$
test_cql_speed 39.3424ms 37.4007ms 26.7375 Ops/s 26.7118 Ops/s $\color{#35bf28}+0.10\%$
test_a2c_speed 8.9733ms 7.7098ms 129.7056 Ops/s 131.4362 Ops/s $\color{#d91a1a}-1.32\%$
test_ppo_speed 9.6086ms 8.1099ms 123.3060 Ops/s 126.8665 Ops/s $\color{#d91a1a}-2.81\%$
test_reinforce_speed 7.4446ms 6.9199ms 144.5104 Ops/s 147.9602 Ops/s $\color{#d91a1a}-2.33\%$
test_iql_speed 34.5452ms 33.7677ms 29.6141 Ops/s 29.9424 Ops/s $\color{#d91a1a}-1.10\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.4785ms 2.3965ms 417.2807 Ops/s 455.9842 Ops/s $\textbf{\color{#d91a1a}-8.49\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8738ms 0.5177ms 1.9318 KOps/s 1.9928 KOps/s $\color{#d91a1a}-3.06\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7904ms 0.5010ms 1.9961 KOps/s 2.0903 KOps/s $\color{#d91a1a}-4.51\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9617ms 2.6060ms 383.7370 Ops/s 481.8652 Ops/s $\textbf{\color{#d91a1a}-20.36\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8724ms 0.5296ms 1.8882 KOps/s 1.9987 KOps/s $\textbf{\color{#d91a1a}-5.53\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.8398ms 0.5052ms 1.9796 KOps/s 2.0932 KOps/s $\textbf{\color{#d91a1a}-5.43\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.8040ms 1.2659ms 789.9663 Ops/s 803.4086 Ops/s $\color{#d91a1a}-1.67\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 4.5032ms 1.2037ms 830.7717 Ops/s 853.1066 Ops/s $\color{#d91a1a}-2.62\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.6745ms 2.6118ms 382.8833 Ops/s 432.5895 Ops/s $\textbf{\color{#d91a1a}-11.49\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2460ms 0.6384ms 1.5664 KOps/s 1.6143 KOps/s $\color{#d91a1a}-2.97\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9683ms 0.6030ms 1.6585 KOps/s 1.6744 KOps/s $\color{#d91a1a}-0.95\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.1966ms 2.1981ms 454.9476 Ops/s 460.0425 Ops/s $\color{#d91a1a}-1.11\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1386ms 0.5054ms 1.9786 KOps/s 1.9713 KOps/s $\color{#35bf28}+0.37\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7720ms 0.4870ms 2.0533 KOps/s 2.0917 KOps/s $\color{#d91a1a}-1.83\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.5514ms 2.2187ms 450.7166 Ops/s 456.4467 Ops/s $\color{#d91a1a}-1.26\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9143ms 0.5658ms 1.7675 KOps/s 1.7998 KOps/s $\color{#d91a1a}-1.79\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6474ms 0.4843ms 2.0649 KOps/s 2.0821 KOps/s $\color{#d91a1a}-0.82\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.4379ms 2.3684ms 422.2294 Ops/s 446.8168 Ops/s $\textbf{\color{#d91a1a}-5.50\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1850ms 0.6412ms 1.5596 KOps/s 1.6142 KOps/s $\color{#d91a1a}-3.38\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9304ms 0.6196ms 1.6140 KOps/s 1.6683 KOps/s $\color{#d91a1a}-3.26\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1209s 8.1811ms 122.2324 Ops/s 123.3480 Ops/s $\color{#d91a1a}-0.90\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 15.9161ms 13.0342ms 76.7212 Ops/s 78.7100 Ops/s $\color{#d91a1a}-2.53\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.7996ms 1.1232ms 890.3273 Ops/s 953.1200 Ops/s $\textbf{\color{#d91a1a}-6.59\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1062s 5.7555ms 173.7457 Ops/s 169.9892 Ops/s $\color{#35bf28}+2.21\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.5025ms 13.4815ms 74.1756 Ops/s 66.2835 Ops/s $\textbf{\color{#35bf28}+11.91\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.8463ms 1.1421ms 875.5713 Ops/s 892.9319 Ops/s $\color{#d91a1a}-1.94\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1117s 8.3219ms 120.1644 Ops/s 168.1975 Ops/s $\textbf{\color{#d91a1a}-28.56\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 15.6368ms 13.3171ms 75.0914 Ops/s 76.2039 Ops/s $\color{#d91a1a}-1.46\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 1.9037ms 1.4165ms 705.9743 Ops/s 695.7408 Ops/s $\color{#35bf28}+1.47\%$

Copy link

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1142s 0.1140s 8.7727 Ops/s 8.6847 Ops/s $\color{#35bf28}+1.01\%$
test_sync 0.1010s 99.6392ms 10.0362 Ops/s 10.0184 Ops/s $\color{#35bf28}+0.18\%$
test_async 0.1870s 95.0372ms 10.5222 Ops/s 10.5632 Ops/s $\color{#d91a1a}-0.39\%$
test_single_pixels 0.1253s 0.1240s 8.0649 Ops/s 7.9841 Ops/s $\color{#35bf28}+1.01\%$
test_sync_pixels 85.0206ms 81.0130ms 12.3437 Ops/s 12.1729 Ops/s $\color{#35bf28}+1.40\%$
test_async_pixels 0.1593s 67.9169ms 14.7239 Ops/s 12.7640 Ops/s $\textbf{\color{#35bf28}+15.36\%}$
test_simple 0.7522s 0.7513s 1.3310 Ops/s 1.3025 Ops/s $\color{#35bf28}+2.19\%$
test_transformed 0.9902s 0.9895s 1.0106 Ops/s 0.9821 Ops/s $\color{#35bf28}+2.90\%$
test_serial 2.4955s 2.4573s 0.4069 Ops/s 0.4106 Ops/s $\color{#d91a1a}-0.89\%$
test_parallel 2.3724s 2.3136s 0.4322 Ops/s 0.4349 Ops/s $\color{#d91a1a}-0.61\%$
test_step_mdp_speed[True-True-True-True-True] 94.5910μs 34.3239μs 29.1343 KOps/s 30.5971 KOps/s $\color{#d91a1a}-4.78\%$
test_step_mdp_speed[True-True-True-True-False] 0.1423ms 20.4681μs 48.8566 KOps/s 51.0996 KOps/s $\color{#d91a1a}-4.39\%$
test_step_mdp_speed[True-True-True-False-True] 35.6510μs 19.2070μs 52.0645 KOps/s 53.0497 KOps/s $\color{#d91a1a}-1.86\%$
test_step_mdp_speed[True-True-True-False-False] 33.8110μs 11.5818μs 86.3425 KOps/s 88.9058 KOps/s $\color{#d91a1a}-2.88\%$
test_step_mdp_speed[True-True-False-True-True] 71.1610μs 36.0555μs 27.7350 KOps/s 29.1179 KOps/s $\color{#d91a1a}-4.75\%$
test_step_mdp_speed[True-True-False-True-False] 83.9510μs 22.0105μs 45.4328 KOps/s 47.1125 KOps/s $\color{#d91a1a}-3.57\%$
test_step_mdp_speed[True-True-False-False-True] 47.0810μs 21.5361μs 46.4338 KOps/s 48.9383 KOps/s $\textbf{\color{#d91a1a}-5.12\%}$
test_step_mdp_speed[True-True-False-False-False] 27.5610μs 13.5162μs 73.9854 KOps/s 76.9255 KOps/s $\color{#d91a1a}-3.82\%$
test_step_mdp_speed[True-False-True-True-True] 58.7210μs 37.9332μs 26.3621 KOps/s 27.6260 KOps/s $\color{#d91a1a}-4.57\%$
test_step_mdp_speed[True-False-True-True-False] 48.1120μs 24.3575μs 41.0552 KOps/s 42.8095 KOps/s $\color{#d91a1a}-4.10\%$
test_step_mdp_speed[True-False-True-False-True] 37.8200μs 20.7700μs 48.1464 KOps/s 48.4833 KOps/s $\color{#d91a1a}-0.69\%$
test_step_mdp_speed[True-False-True-False-False] 37.8610μs 13.5544μs 73.7767 KOps/s 75.6169 KOps/s $\color{#d91a1a}-2.43\%$
test_step_mdp_speed[True-False-False-True-True] 62.2410μs 40.1276μs 24.9205 KOps/s 26.4217 KOps/s $\textbf{\color{#d91a1a}-5.68\%}$
test_step_mdp_speed[True-False-False-True-False] 45.7510μs 26.1976μs 38.1714 KOps/s 40.0426 KOps/s $\color{#d91a1a}-4.67\%$
test_step_mdp_speed[True-False-False-False-True] 39.0000μs 22.9804μs 43.5154 KOps/s 44.8832 KOps/s $\color{#d91a1a}-3.05\%$
test_step_mdp_speed[True-False-False-False-False] 28.6100μs 15.2516μs 65.5668 KOps/s 66.8997 KOps/s $\color{#d91a1a}-1.99\%$
test_step_mdp_speed[False-True-True-True-True] 0.1110ms 38.3659μs 26.0648 KOps/s 27.8134 KOps/s $\textbf{\color{#d91a1a}-6.29\%}$
test_step_mdp_speed[False-True-True-True-False] 47.1810μs 23.9726μs 41.7143 KOps/s 42.8265 KOps/s $\color{#d91a1a}-2.60\%$
test_step_mdp_speed[False-True-True-False-True] 0.2115ms 25.1634μs 39.7403 KOps/s 41.7361 KOps/s $\color{#d91a1a}-4.78\%$
test_step_mdp_speed[False-True-True-False-False] 29.4500μs 15.1763μs 65.8920 KOps/s 67.4299 KOps/s $\color{#d91a1a}-2.28\%$
test_step_mdp_speed[False-True-False-True-True] 98.4510μs 39.7386μs 25.1644 KOps/s 26.5923 KOps/s $\textbf{\color{#d91a1a}-5.37\%}$
test_step_mdp_speed[False-True-False-True-False] 90.4610μs 25.7041μs 38.9043 KOps/s 39.9873 KOps/s $\color{#d91a1a}-2.71\%$
test_step_mdp_speed[False-True-False-False-True] 44.4910μs 27.5012μs 36.3621 KOps/s 38.9478 KOps/s $\textbf{\color{#d91a1a}-6.64\%}$
test_step_mdp_speed[False-True-False-False-False] 32.8500μs 17.0478μs 58.6586 KOps/s 59.9704 KOps/s $\color{#d91a1a}-2.19\%$
test_step_mdp_speed[False-False-True-True-True] 64.7710μs 41.5427μs 24.0716 KOps/s 24.9141 KOps/s $\color{#d91a1a}-3.38\%$
test_step_mdp_speed[False-False-True-True-False] 43.9900μs 27.6744μs 36.1344 KOps/s 36.8055 KOps/s $\color{#d91a1a}-1.82\%$
test_step_mdp_speed[False-False-True-False-True] 48.3000μs 27.3238μs 36.5982 KOps/s 38.9429 KOps/s $\textbf{\color{#d91a1a}-6.02\%}$
test_step_mdp_speed[False-False-True-False-False] 41.1010μs 17.1388μs 58.3472 KOps/s 60.3902 KOps/s $\color{#d91a1a}-3.38\%$
test_step_mdp_speed[False-False-False-True-True] 73.6110μs 44.1201μs 22.6654 KOps/s 23.5115 KOps/s $\color{#d91a1a}-3.60\%$
test_step_mdp_speed[False-False-False-True-False] 47.8710μs 30.0598μs 33.2671 KOps/s 34.1153 KOps/s $\color{#d91a1a}-2.49\%$
test_step_mdp_speed[False-False-False-False-True] 50.4910μs 28.9183μs 34.5802 KOps/s 36.8601 KOps/s $\textbf{\color{#d91a1a}-6.19\%}$
test_step_mdp_speed[False-False-False-False-False] 0.1924ms 19.0387μs 52.5247 KOps/s 54.6164 KOps/s $\color{#d91a1a}-3.83\%$
test_values[generalized_advantage_estimate-True-True] 26.4102ms 25.4114ms 39.3524 Ops/s 39.3692 Ops/s $\color{#d91a1a}-0.04\%$
test_values[vec_generalized_advantage_estimate-True-True] 87.3527ms 3.3103ms 302.0919 Ops/s 316.9506 Ops/s $\color{#d91a1a}-4.69\%$
test_values[td0_return_estimate-False-False] 0.2160ms 66.6478μs 15.0043 KOps/s 15.4614 KOps/s $\color{#d91a1a}-2.96\%$
test_values[td1_return_estimate-False-False] 54.2082ms 53.8861ms 18.5577 Ops/s 18.5106 Ops/s $\color{#35bf28}+0.25\%$
test_values[vec_td1_return_estimate-False-False] 2.0908ms 1.7682ms 565.5531 Ops/s 567.0359 Ops/s $\color{#d91a1a}-0.26\%$
test_values[td_lambda_return_estimate-True-False] 85.5633ms 84.9863ms 11.7666 Ops/s 11.7531 Ops/s $\color{#35bf28}+0.11\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.1093ms 1.7613ms 567.7700 Ops/s 567.0104 Ops/s $\color{#35bf28}+0.13\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.1849ms 23.8818ms 41.8729 Ops/s 39.8367 Ops/s $\textbf{\color{#35bf28}+5.11\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8873ms 0.6984ms 1.4319 KOps/s 1.3862 KOps/s $\color{#35bf28}+3.29\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7050ms 0.6479ms 1.5435 KOps/s 1.5221 KOps/s $\color{#35bf28}+1.41\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6069ms 1.4528ms 688.3192 Ops/s 685.0620 Ops/s $\color{#35bf28}+0.48\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9428ms 0.6677ms 1.4976 KOps/s 1.4933 KOps/s $\color{#35bf28}+0.29\%$
test_dqn_speed 1.7637ms 1.4368ms 695.9722 Ops/s 692.6321 Ops/s $\color{#35bf28}+0.48\%$
test_ddpg_speed 3.1724ms 2.9263ms 341.7238 Ops/s 335.2410 Ops/s $\color{#35bf28}+1.93\%$
test_sac_speed 8.9333ms 8.5798ms 116.5534 Ops/s 116.2900 Ops/s $\color{#35bf28}+0.23\%$
test_redq_speed 11.2406ms 10.2902ms 97.1798 Ops/s 96.1802 Ops/s $\color{#35bf28}+1.04\%$
test_redq_deprec_speed 12.1854ms 11.6795ms 85.6199 Ops/s 84.8503 Ops/s $\color{#35bf28}+0.91\%$
test_td3_speed 17.4529ms 8.5065ms 117.5574 Ops/s 118.0565 Ops/s $\color{#d91a1a}-0.42\%$
test_cql_speed 27.5872ms 26.3055ms 38.0149 Ops/s 37.9296 Ops/s $\color{#35bf28}+0.22\%$
test_a2c_speed 6.4599ms 5.8141ms 171.9955 Ops/s 171.7307 Ops/s $\color{#35bf28}+0.15\%$
test_ppo_speed 6.3070ms 6.0829ms 164.3940 Ops/s 163.5215 Ops/s $\color{#35bf28}+0.53\%$
test_reinforce_speed 4.9671ms 4.7075ms 212.4263 Ops/s 212.5896 Ops/s $\color{#d91a1a}-0.08\%$
test_iql_speed 20.9189ms 20.3216ms 49.2087 Ops/s 50.0194 Ops/s $\color{#d91a1a}-1.62\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0683ms 2.8158ms 355.1418 Ops/s 356.0969 Ops/s $\color{#d91a1a}-0.27\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7937ms 0.5975ms 1.6737 KOps/s 1.6649 KOps/s $\color{#35bf28}+0.52\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.3112ms 0.5765ms 1.7345 KOps/s 1.7373 KOps/s $\color{#d91a1a}-0.16\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1569ms 2.8526ms 350.5577 Ops/s 355.2070 Ops/s $\color{#d91a1a}-1.31\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7071ms 0.5890ms 1.6977 KOps/s 1.6920 KOps/s $\color{#35bf28}+0.34\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.1748ms 0.5686ms 1.7587 KOps/s 1.7538 KOps/s $\color{#35bf28}+0.28\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7426ms 1.5393ms 649.6464 Ops/s 644.5445 Ops/s $\color{#35bf28}+0.79\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6543ms 1.4684ms 681.0125 Ops/s 669.5001 Ops/s $\color{#35bf28}+1.72\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.0777ms 2.9132ms 343.2665 Ops/s 339.2388 Ops/s $\color{#35bf28}+1.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2829ms 0.7223ms 1.3845 KOps/s 1.3729 KOps/s $\color{#35bf28}+0.85\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9833ms 0.7025ms 1.4235 KOps/s 1.4281 KOps/s $\color{#d91a1a}-0.32\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.9284ms 2.8172ms 354.9679 Ops/s 356.2111 Ops/s $\color{#d91a1a}-0.35\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7149ms 0.5972ms 1.6746 KOps/s 1.6606 KOps/s $\color{#35bf28}+0.84\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.3866ms 0.5793ms 1.7264 KOps/s 1.7234 KOps/s $\color{#35bf28}+0.17\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.9959ms 2.8407ms 352.0212 Ops/s 356.1039 Ops/s $\color{#d91a1a}-1.15\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.5018ms 0.5919ms 1.6895 KOps/s 1.6848 KOps/s $\color{#35bf28}+0.28\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6608ms 0.5629ms 1.7764 KOps/s 1.7386 KOps/s $\color{#35bf28}+2.18\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.0548ms 2.9522ms 338.7249 Ops/s 340.4229 Ops/s $\color{#d91a1a}-0.50\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9097ms 0.7276ms 1.3744 KOps/s 1.3702 KOps/s $\color{#35bf28}+0.31\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8796ms 0.7068ms 1.4149 KOps/s 1.4228 KOps/s $\color{#d91a1a}-0.55\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1214s 7.3010ms 136.9684 Ops/s 103.3220 Ops/s $\textbf{\color{#35bf28}+32.56\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 17.9515ms 15.4250ms 64.8298 Ops/s 63.4945 Ops/s $\color{#35bf28}+2.10\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.2358ms 1.1655ms 858.0222 Ops/s 715.5434 Ops/s $\textbf{\color{#35bf28}+19.91\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1180s 9.4079ms 106.2938 Ops/s 139.8149 Ops/s $\textbf{\color{#d91a1a}-23.98\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 17.7745ms 15.4413ms 64.7614 Ops/s 63.2651 Ops/s $\color{#35bf28}+2.37\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.2469ms 1.1631ms 859.7793 Ops/s 703.9204 Ops/s $\textbf{\color{#35bf28}+22.14\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1151s 7.5098ms 133.1600 Ops/s 132.2181 Ops/s $\color{#35bf28}+0.71\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.3558ms 15.7022ms 63.6853 Ops/s 62.1547 Ops/s $\color{#35bf28}+2.46\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 3.0503ms 1.6813ms 594.7633 Ops/s 627.6560 Ops/s $\textbf{\color{#d91a1a}-5.24\%}$

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.

None yet

3 participants