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.

Sign up for GitHub

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

Jump to bottom

[Feature] Better repr of RBs #1991

Merged
merged 2 commits into from
Mar 4, 2024
Merged

[Feature] Better repr of RBs #1991

merged 2 commits into from
Mar 4, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Mar 4, 2024 •
edited
Loading

No description provided.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Mar 4, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1991

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

✅ No Failures

As of commit ee99ce4 with merge base 3a41f40 (image):
💚 Looks good so far! There are no failures yet. 💚

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 Mar 4, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 4, 2024 •
edited
Loading

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}23$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 61.4360ms 60.3425ms 16.5721 Ops/s 15.7573 Ops/s $\textbf{\color{#35bf28}+5.17\%}$
test_sync 38.9740ms 33.4010ms 29.9392 Ops/s 30.4238 Ops/s $\color{#d91a1a}-1.59\%$
test_async 60.8812ms 30.4754ms 32.8133 Ops/s 33.8990 Ops/s $\color{#d91a1a}-3.20\%$
test_simple 0.4871s 0.4263s 2.3456 Ops/s 2.4158 Ops/s $\color{#d91a1a}-2.90\%$
test_transformed 0.6366s 0.5785s 1.7285 Ops/s 1.7020 Ops/s $\color{#35bf28}+1.56\%$
test_serial 1.4336s 1.3762s 0.7266 Ops/s 0.7128 Ops/s $\color{#35bf28}+1.94\%$
test_parallel 1.3906s 1.3468s 0.7425 Ops/s 0.7421 Ops/s $\color{#35bf28}+0.06\%$
test_step_mdp_speed[True-True-True-True-True] 76.5620μs 21.5585μs 46.3854 KOps/s 45.1280 KOps/s $\color{#35bf28}+2.79\%$
test_step_mdp_speed[True-True-True-True-False] 38.9320μs 13.1939μs 75.7923 KOps/s 75.8778 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[True-True-True-False-True] 59.3600μs 12.6688μs 78.9339 KOps/s 79.0244 KOps/s $\color{#d91a1a}-0.11\%$
test_step_mdp_speed[True-True-True-False-False] 38.5110μs 7.6826μs 130.1636 KOps/s 131.7075 KOps/s $\color{#d91a1a}-1.17\%$
test_step_mdp_speed[True-True-False-True-True] 68.9680μs 23.2234μs 43.0600 KOps/s 42.1779 KOps/s $\color{#35bf28}+2.09\%$
test_step_mdp_speed[True-True-False-True-False] 62.4760μs 14.4001μs 69.4440 KOps/s 68.9248 KOps/s $\color{#35bf28}+0.75\%$
test_step_mdp_speed[True-True-False-False-True] 64.6000μs 14.0024μs 71.4164 KOps/s 70.9654 KOps/s $\color{#35bf28}+0.64\%$
test_step_mdp_speed[True-True-False-False-False] 34.9550μs 8.9484μs 111.7522 KOps/s 111.9469 KOps/s $\color{#d91a1a}-0.17\%$
test_step_mdp_speed[True-False-True-True-True] 77.7050μs 24.3157μs 41.1257 KOps/s 39.7677 KOps/s $\color{#35bf28}+3.41\%$
test_step_mdp_speed[True-False-True-True-False] 58.6200μs 16.1228μs 62.0239 KOps/s 62.3559 KOps/s $\color{#d91a1a}-0.53\%$
test_step_mdp_speed[True-False-True-False-True] 64.5700μs 13.8884μs 72.0025 KOps/s 70.8969 KOps/s $\color{#35bf28}+1.56\%$
test_step_mdp_speed[True-False-True-False-False] 28.7330μs 8.9947μs 111.1771 KOps/s 111.7709 KOps/s $\color{#d91a1a}-0.53\%$
test_step_mdp_speed[True-False-False-True-True] 79.5380μs 25.5077μs 39.2039 KOps/s 37.7555 KOps/s $\color{#35bf28}+3.84\%$
test_step_mdp_speed[True-False-False-True-False] 66.7240μs 17.0967μs 58.4910 KOps/s 58.0908 KOps/s $\color{#35bf28}+0.69\%$
test_step_mdp_speed[True-False-False-False-True] 72.2150μs 15.0206μs 66.5751 KOps/s 64.2153 KOps/s $\color{#35bf28}+3.67\%$
test_step_mdp_speed[True-False-False-False-False] 0.1489ms 10.7616μs 92.9233 KOps/s 97.9124 KOps/s $\textbf{\color{#d91a1a}-5.10\%}$
test_step_mdp_speed[False-True-True-True-True] 64.8200μs 24.5729μs 40.6953 KOps/s 39.7022 KOps/s $\color{#35bf28}+2.50\%$
test_step_mdp_speed[False-True-True-True-False] 43.3710μs 15.8602μs 63.0507 KOps/s 62.2289 KOps/s $\color{#35bf28}+1.32\%$
test_step_mdp_speed[False-True-True-False-True] 73.0260μs 16.3335μs 61.2239 KOps/s 60.1900 KOps/s $\color{#35bf28}+1.72\%$
test_step_mdp_speed[False-True-True-False-False] 38.5710μs 10.2006μs 98.0337 KOps/s 97.6598 KOps/s $\color{#35bf28}+0.38\%$
test_step_mdp_speed[False-True-False-True-True] 51.0960μs 25.7752μs 38.7970 KOps/s 37.2305 KOps/s $\color{#35bf28}+4.21\%$
test_step_mdp_speed[False-True-False-True-False] 57.5470μs 17.1161μs 58.4246 KOps/s 58.5365 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[False-True-False-False-True] 47.6380μs 17.3493μs 57.6391 KOps/s 55.8927 KOps/s $\color{#35bf28}+3.12\%$
test_step_mdp_speed[False-True-False-False-False] 60.8230μs 11.3715μs 87.9391 KOps/s 86.9569 KOps/s $\color{#35bf28}+1.13\%$
test_step_mdp_speed[False-False-True-True-True] 57.7380μs 26.9049μs 37.1679 KOps/s 35.5884 KOps/s $\color{#35bf28}+4.44\%$
test_step_mdp_speed[False-False-True-True-False] 78.8560μs 18.3913μs 54.3734 KOps/s 53.7470 KOps/s $\color{#35bf28}+1.17\%$
test_step_mdp_speed[False-False-True-False-True] 66.7440μs 17.3443μs 57.6558 KOps/s 55.5949 KOps/s $\color{#35bf28}+3.71\%$
test_step_mdp_speed[False-False-True-False-False] 41.4970μs 11.3355μs 88.2185 KOps/s 86.0756 KOps/s $\color{#35bf28}+2.49\%$
test_step_mdp_speed[False-False-False-True-True] 0.2153ms 27.8469μs 35.9106 KOps/s 34.1547 KOps/s $\textbf{\color{#35bf28}+5.14\%}$
test_step_mdp_speed[False-False-False-True-False] 46.0350μs 19.3680μs 51.6316 KOps/s 50.3979 KOps/s $\color{#35bf28}+2.45\%$
test_step_mdp_speed[False-False-False-False-True] 66.8840μs 18.1507μs 55.0943 KOps/s 52.1439 KOps/s $\textbf{\color{#35bf28}+5.66\%}$
test_step_mdp_speed[False-False-False-False-False] 39.7430μs 12.4460μs 80.3468 KOps/s 78.1531 KOps/s $\color{#35bf28}+2.81\%$
test_values[generalized_advantage_estimate-True-True] 12.2702ms 9.3173ms 107.3275 Ops/s 108.0905 Ops/s $\color{#d91a1a}-0.71\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.2170ms 33.5147ms 29.8377 Ops/s 29.3422 Ops/s $\color{#35bf28}+1.69\%$
test_values[td0_return_estimate-False-False] 0.2462ms 0.1869ms 5.3497 KOps/s 5.8260 KOps/s $\textbf{\color{#d91a1a}-8.17\%}$
test_values[td1_return_estimate-False-False] 27.1942ms 23.9091ms 41.8251 Ops/s 42.9724 Ops/s $\color{#d91a1a}-2.67\%$
test_values[vec_td1_return_estimate-False-False] 35.5162ms 33.6715ms 29.6987 Ops/s 29.8027 Ops/s $\color{#d91a1a}-0.35\%$
test_values[td_lambda_return_estimate-True-False] 37.5734ms 33.3228ms 30.0095 Ops/s 28.9399 Ops/s $\color{#35bf28}+3.70\%$
test_values[vec_td_lambda_return_estimate-True-False] 35.6029ms 33.4819ms 29.8669 Ops/s 28.3076 Ops/s $\textbf{\color{#35bf28}+5.51\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 12.5672ms 8.2361ms 121.4171 Ops/s 122.9005 Ops/s $\color{#d91a1a}-1.21\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3356ms 2.0449ms 489.0305 Ops/s 534.6766 Ops/s $\textbf{\color{#d91a1a}-8.54\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4767ms 0.3496ms 2.8601 KOps/s 2.7639 KOps/s $\color{#35bf28}+3.48\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 54.0075ms 41.9967ms 23.8114 Ops/s 23.1576 Ops/s $\color{#35bf28}+2.82\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.6440ms 3.0355ms 329.4330 Ops/s 321.4108 Ops/s $\color{#35bf28}+2.50\%$
test_dqn_speed 6.5591ms 1.3583ms 736.2024 Ops/s 719.1431 Ops/s $\color{#35bf28}+2.37\%$
test_ddpg_speed 3.4029ms 2.6762ms 373.6691 Ops/s 367.4193 Ops/s $\color{#35bf28}+1.70\%$
test_sac_speed 9.5727ms 8.0749ms 123.8408 Ops/s 122.3770 Ops/s $\color{#35bf28}+1.20\%$
test_redq_speed 14.9282ms 13.1153ms 76.2468 Ops/s 75.8001 Ops/s $\color{#35bf28}+0.59\%$
test_redq_deprec_speed 13.8397ms 12.7742ms 78.2825 Ops/s 74.9543 Ops/s $\color{#35bf28}+4.44\%$
test_td3_speed 15.2136ms 8.1192ms 123.1645 Ops/s 122.4759 Ops/s $\color{#35bf28}+0.56\%$
test_cql_speed 37.9691ms 36.2588ms 27.5795 Ops/s 27.0627 Ops/s $\color{#35bf28}+1.91\%$
test_a2c_speed 8.1866ms 7.4308ms 134.5750 Ops/s 131.2512 Ops/s $\color{#35bf28}+2.53\%$
test_ppo_speed 8.7679ms 7.5752ms 132.0089 Ops/s 129.2168 Ops/s $\color{#35bf28}+2.16\%$
test_reinforce_speed 7.3835ms 6.6063ms 151.3710 Ops/s 151.5157 Ops/s $\color{#d91a1a}-0.10\%$
test_iql_speed 33.5353ms 32.2860ms 30.9732 Ops/s 30.3691 Ops/s $\color{#35bf28}+1.99\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.5277ms 2.2442ms 445.5897 Ops/s 428.5989 Ops/s $\color{#35bf28}+3.96\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.4075ms 0.4995ms 2.0019 KOps/s 1.9501 KOps/s $\color{#35bf28}+2.66\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7986ms 0.4677ms 2.1380 KOps/s 1.9665 KOps/s $\textbf{\color{#35bf28}+8.72\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.5766ms 2.1751ms 459.7428 Ops/s 406.7996 Ops/s $\textbf{\color{#35bf28}+13.01\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.4450ms 0.4983ms 2.0070 KOps/s 1.9848 KOps/s $\color{#35bf28}+1.12\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.5176ms 0.4562ms 2.1922 KOps/s 2.0768 KOps/s $\textbf{\color{#35bf28}+5.56\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.4672ms 2.1768ms 459.3943 Ops/s 341.8879 Ops/s $\textbf{\color{#35bf28}+34.37\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8508ms 0.5953ms 1.6798 KOps/s 1.5644 KOps/s $\textbf{\color{#35bf28}+7.38\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 3.7244ms 0.5745ms 1.7407 KOps/s 1.6436 KOps/s $\textbf{\color{#35bf28}+5.91\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.7609ms 2.1102ms 473.8951 Ops/s 376.3568 Ops/s $\textbf{\color{#35bf28}+25.92\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5832ms 0.4827ms 2.0718 KOps/s 1.8887 KOps/s $\textbf{\color{#35bf28}+9.69\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 3.5978ms 0.4670ms 2.1415 KOps/s 2.0076 KOps/s $\textbf{\color{#35bf28}+6.67\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.3270ms 2.1330ms 468.8245 Ops/s 376.4777 Ops/s $\textbf{\color{#35bf28}+24.53\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7578ms 0.4840ms 2.0661 KOps/s 1.9407 KOps/s $\textbf{\color{#35bf28}+6.46\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6054ms 0.4538ms 2.2038 KOps/s 2.0207 KOps/s $\textbf{\color{#35bf28}+9.06\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.6793ms 2.3221ms 430.6361 Ops/s 376.9079 Ops/s $\textbf{\color{#35bf28}+14.26\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0664ms 0.6005ms 1.6653 KOps/s 1.5690 KOps/s $\textbf{\color{#35bf28}+6.14\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7055ms 0.5689ms 1.7579 KOps/s 1.6537 KOps/s $\textbf{\color{#35bf28}+6.30\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1007s 7.1683ms 139.5036 Ops/s 130.6850 Ops/s $\textbf{\color{#35bf28}+6.75\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.2080ms 11.8511ms 84.3807 Ops/s 82.4442 Ops/s $\color{#35bf28}+2.35\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.6156ms 1.0505ms 951.9376 Ops/s 927.4772 Ops/s $\color{#35bf28}+2.64\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1002s 7.4007ms 135.1224 Ops/s 137.3693 Ops/s $\color{#d91a1a}-1.64\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.4079ms 11.8747ms 84.2126 Ops/s 82.0885 Ops/s $\color{#35bf28}+2.59\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.5330ms 1.0334ms 967.6749 Ops/s 915.6289 Ops/s $\textbf{\color{#35bf28}+5.68\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 93.0892ms 5.6782ms 176.1124 Ops/s 129.4159 Ops/s $\textbf{\color{#35bf28}+36.08\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.6326ms 12.3462ms 80.9964 Ops/s 80.0836 Ops/s $\color{#35bf28}+1.14\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.1035ms 1.3720ms 728.8821 Ops/s 684.4946 Ops/s $\textbf{\color{#35bf28}+6.48\%}$

@vmoens vmoens mentioned this pull request Mar 4, 2024
Closed
@vmoens vmoens linked an issue Mar 4, 2024 that may be closed by this pull request
[Feature Request] ReplayBuffer element display and store None #1986
Closed
@vmoens vmoens marked this pull request as ready for review March 4, 2024 12:38
@github-actions GitHub Actions
Copy link

github-actions bot commented Mar 4, 2024 •
edited
Loading

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}8$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1104s 0.1102s 9.0749 Ops/s 8.7775 Ops/s $\color{#35bf28}+3.39\%$
test_sync 95.1811ms 94.7357ms 10.5557 Ops/s 10.5337 Ops/s $\color{#35bf28}+0.21\%$
test_async 0.1857s 92.9169ms 10.7623 Ops/s 10.7837 Ops/s $\color{#d91a1a}-0.20\%$
test_single_pixels 0.1221s 0.1215s 8.2284 Ops/s 7.9988 Ops/s $\color{#35bf28}+2.87\%$
test_sync_pixels 81.3715ms 76.1628ms 13.1298 Ops/s 12.3294 Ops/s $\textbf{\color{#35bf28}+6.49\%}$
test_async_pixels 0.1388s 71.2005ms 14.0448 Ops/s 15.5997 Ops/s $\textbf{\color{#d91a1a}-9.97\%}$
test_simple 0.8785s 0.8147s 1.2274 Ops/s 1.2038 Ops/s $\color{#35bf28}+1.96\%$
test_transformed 1.0946s 1.0386s 0.9628 Ops/s 0.9438 Ops/s $\color{#35bf28}+2.02\%$
test_serial 2.4171s 2.3618s 0.4234 Ops/s 0.4046 Ops/s $\color{#35bf28}+4.64\%$
test_parallel 2.1101s 2.0569s 0.4862 Ops/s 0.4723 Ops/s $\color{#35bf28}+2.95\%$
test_step_mdp_speed[True-True-True-True-True] 0.1149ms 32.6001μs 30.6748 KOps/s 30.6725 KOps/s $+0.01\%$
test_step_mdp_speed[True-True-True-True-False] 45.3200μs 19.2354μs 51.9876 KOps/s 49.9933 KOps/s $\color{#35bf28}+3.99\%$
test_step_mdp_speed[True-True-True-False-True] 40.5710μs 18.4874μs 54.0910 KOps/s 53.2437 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[True-True-True-False-False] 29.1010μs 10.9928μs 90.9686 KOps/s 88.1429 KOps/s $\color{#35bf28}+3.21\%$
test_step_mdp_speed[True-True-False-True-True] 57.2020μs 34.3165μs 29.1405 KOps/s 28.6222 KOps/s $\color{#35bf28}+1.81\%$
test_step_mdp_speed[True-True-False-True-False] 37.0900μs 21.0303μs 47.5505 KOps/s 45.8108 KOps/s $\color{#35bf28}+3.80\%$
test_step_mdp_speed[True-True-False-False-True] 44.6810μs 20.2598μs 49.3589 KOps/s 48.6080 KOps/s $\color{#35bf28}+1.54\%$
test_step_mdp_speed[True-True-False-False-False] 30.7500μs 12.9321μs 77.3269 KOps/s 76.1135 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[True-False-True-True-True] 64.0120μs 36.3363μs 27.5207 KOps/s 27.0189 KOps/s $\color{#35bf28}+1.86\%$
test_step_mdp_speed[True-False-True-True-False] 43.3510μs 23.4346μs 42.6720 KOps/s 41.7442 KOps/s $\color{#35bf28}+2.22\%$
test_step_mdp_speed[True-False-True-False-True] 45.2410μs 19.9109μs 50.2237 KOps/s 48.6089 KOps/s $\color{#35bf28}+3.32\%$
test_step_mdp_speed[True-False-True-False-False] 29.1210μs 12.8236μs 77.9810 KOps/s 75.8318 KOps/s $\color{#35bf28}+2.83\%$
test_step_mdp_speed[True-False-False-True-True] 66.2010μs 37.9580μs 26.3449 KOps/s 25.7706 KOps/s $\color{#35bf28}+2.23\%$
test_step_mdp_speed[True-False-False-True-False] 41.0010μs 24.8509μs 40.2400 KOps/s 38.7186 KOps/s $\color{#35bf28}+3.93\%$
test_step_mdp_speed[True-False-False-False-True] 39.5110μs 21.9323μs 45.5949 KOps/s 44.8151 KOps/s $\color{#35bf28}+1.74\%$
test_step_mdp_speed[True-False-False-False-False] 31.8610μs 14.7541μs 67.7779 KOps/s 66.1026 KOps/s $\color{#35bf28}+2.53\%$
test_step_mdp_speed[False-True-True-True-True] 57.3210μs 35.9391μs 27.8248 KOps/s 27.1071 KOps/s $\color{#35bf28}+2.65\%$
test_step_mdp_speed[False-True-True-True-False] 48.7410μs 23.2225μs 43.0617 KOps/s 41.3921 KOps/s $\color{#35bf28}+4.03\%$
test_step_mdp_speed[False-True-True-False-True] 50.4910μs 23.9421μs 41.7674 KOps/s 40.8455 KOps/s $\color{#35bf28}+2.26\%$
test_step_mdp_speed[False-True-True-False-False] 31.9200μs 14.6772μs 68.1331 KOps/s 65.4219 KOps/s $\color{#35bf28}+4.14\%$
test_step_mdp_speed[False-True-False-True-True] 63.1500μs 38.5618μs 25.9324 KOps/s 26.0543 KOps/s $\color{#d91a1a}-0.47\%$
test_step_mdp_speed[False-True-False-True-False] 43.4410μs 25.1211μs 39.8072 KOps/s 38.9681 KOps/s $\color{#35bf28}+2.15\%$
test_step_mdp_speed[False-True-False-False-True] 57.5210μs 26.0361μs 38.4082 KOps/s 37.9876 KOps/s $\color{#35bf28}+1.11\%$
test_step_mdp_speed[False-True-False-False-False] 0.1916ms 16.5628μs 60.3764 KOps/s 58.1237 KOps/s $\color{#35bf28}+3.88\%$
test_step_mdp_speed[False-False-True-True-True] 65.9310μs 39.6081μs 25.2474 KOps/s 24.5428 KOps/s $\color{#35bf28}+2.87\%$
test_step_mdp_speed[False-False-True-True-False] 45.3410μs 26.7232μs 37.4206 KOps/s 35.8661 KOps/s $\color{#35bf28}+4.33\%$
test_step_mdp_speed[False-False-True-False-True] 49.7300μs 25.8569μs 38.6743 KOps/s 38.0076 KOps/s $\color{#35bf28}+1.75\%$
test_step_mdp_speed[False-False-True-False-False] 35.2910μs 16.3101μs 61.3115 KOps/s 58.3043 KOps/s $\textbf{\color{#35bf28}+5.16\%}$
test_step_mdp_speed[False-False-False-True-True] 64.9910μs 41.0219μs 24.3772 KOps/s 23.6293 KOps/s $\color{#35bf28}+3.17\%$
test_step_mdp_speed[False-False-False-True-False] 49.4410μs 28.6077μs 34.9556 KOps/s 33.7033 KOps/s $\color{#35bf28}+3.72\%$
test_step_mdp_speed[False-False-False-False-True] 54.4410μs 27.5307μs 36.3231 KOps/s 35.7107 KOps/s $\color{#35bf28}+1.72\%$
test_step_mdp_speed[False-False-False-False-False] 43.0600μs 18.2439μs 54.8130 KOps/s 53.2727 KOps/s $\color{#35bf28}+2.89\%$
test_values[generalized_advantage_estimate-True-True] 24.6184ms 24.1104ms 41.4759 Ops/s 39.6123 Ops/s $\color{#35bf28}+4.70\%$
test_values[vec_generalized_advantage_estimate-True-True] 89.7150ms 3.3577ms 297.8253 Ops/s 292.5024 Ops/s $\color{#35bf28}+1.82\%$
test_values[td0_return_estimate-False-False] 93.7020μs 62.6114μs 15.9715 KOps/s 15.0481 KOps/s $\textbf{\color{#35bf28}+6.14\%}$
test_values[td1_return_estimate-False-False] 55.2057ms 54.5725ms 18.3243 Ops/s 18.5154 Ops/s $\color{#d91a1a}-1.03\%$
test_values[vec_td1_return_estimate-False-False] 2.1481ms 1.7618ms 567.5917 Ops/s 560.7185 Ops/s $\color{#35bf28}+1.23\%$
test_values[td_lambda_return_estimate-True-False] 88.6392ms 87.3380ms 11.4498 Ops/s 11.5276 Ops/s $\color{#d91a1a}-0.68\%$
test_values[vec_td_lambda_return_estimate-True-False] 2.1028ms 1.7551ms 569.7794 Ops/s 561.8543 Ops/s $\color{#35bf28}+1.41\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.4674ms 24.1789ms 41.3584 Ops/s 41.8520 Ops/s $\color{#d91a1a}-1.18\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.8633ms 0.6867ms 1.4562 KOps/s 1.3832 KOps/s $\textbf{\color{#35bf28}+5.28\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6968ms 0.6427ms 1.5559 KOps/s 1.5116 KOps/s $\color{#35bf28}+2.93\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5415ms 1.4435ms 692.7416 Ops/s 681.0586 Ops/s $\color{#35bf28}+1.72\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9183ms 0.6632ms 1.5078 KOps/s 1.4650 KOps/s $\color{#35bf28}+2.93\%$
test_dqn_speed 7.9122ms 1.4042ms 712.1517 Ops/s 673.8338 Ops/s $\textbf{\color{#35bf28}+5.69\%}$
test_ddpg_speed 3.0449ms 2.6650ms 375.2400 Ops/s 362.1397 Ops/s $\color{#35bf28}+3.62\%$
test_sac_speed 8.4481ms 7.9665ms 125.5251 Ops/s 121.1816 Ops/s $\color{#35bf28}+3.58\%$
test_redq_speed 10.8458ms 10.1762ms 98.2685 Ops/s 88.7174 Ops/s $\textbf{\color{#35bf28}+10.77\%}$
test_redq_deprec_speed 11.4255ms 10.9291ms 91.4987 Ops/s 84.9751 Ops/s $\textbf{\color{#35bf28}+7.68\%}$
test_td3_speed 15.4631ms 7.9278ms 126.1384 Ops/s 122.8247 Ops/s $\color{#35bf28}+2.70\%$
test_cql_speed 25.9178ms 24.9409ms 40.0947 Ops/s 39.3904 Ops/s $\color{#35bf28}+1.79\%$
test_a2c_speed 5.6566ms 5.3874ms 185.6198 Ops/s 187.2026 Ops/s $\color{#d91a1a}-0.85\%$
test_ppo_speed 6.0944ms 5.7145ms 174.9932 Ops/s 178.0297 Ops/s $\color{#d91a1a}-1.71\%$
test_reinforce_speed 4.6363ms 4.4104ms 226.7371 Ops/s 235.4739 Ops/s $\color{#d91a1a}-3.71\%$
test_iql_speed 20.0544ms 19.0632ms 52.4571 Ops/s 51.9913 Ops/s $\color{#35bf28}+0.90\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0443ms 2.8557ms 350.1807 Ops/s 341.7136 Ops/s $\color{#35bf28}+2.48\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6828ms 0.5412ms 1.8477 KOps/s 1.8106 KOps/s $\color{#35bf28}+2.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7234ms 0.5160ms 1.9381 KOps/s 1.8881 KOps/s $\color{#35bf28}+2.65\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.0130ms 2.8679ms 348.6878 Ops/s 339.0986 Ops/s $\color{#35bf28}+2.83\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8608ms 0.5306ms 1.8847 KOps/s 1.8363 KOps/s $\color{#35bf28}+2.64\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.2804ms 0.5113ms 1.9558 KOps/s 1.9108 KOps/s $\color{#35bf28}+2.35\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.0678ms 2.9744ms 336.1978 Ops/s 327.1900 Ops/s $\color{#35bf28}+2.75\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7891ms 0.6623ms 1.5099 KOps/s 1.4723 KOps/s $\color{#35bf28}+2.55\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8521ms 0.6462ms 1.5476 KOps/s 1.5219 KOps/s $\color{#35bf28}+1.69\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.9235ms 2.8578ms 349.9231 Ops/s 340.9997 Ops/s $\color{#35bf28}+2.62\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6684ms 0.5386ms 1.8567 KOps/s 1.8098 KOps/s $\color{#35bf28}+2.59\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7217ms 0.5192ms 1.9261 KOps/s 1.9010 KOps/s $\color{#35bf28}+1.32\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.0104ms 2.8884ms 346.2091 Ops/s 337.2799 Ops/s $\color{#35bf28}+2.65\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1195ms 0.5373ms 1.8611 KOps/s 1.8273 KOps/s $\color{#35bf28}+1.85\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6854ms 0.5131ms 1.9491 KOps/s 1.9096 KOps/s $\color{#35bf28}+2.07\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1562ms 2.9796ms 335.6182 Ops/s 326.8967 Ops/s $\color{#35bf28}+2.67\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7786ms 0.6657ms 1.5023 KOps/s 1.4695 KOps/s $\color{#35bf28}+2.23\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8353ms 0.6399ms 1.5627 KOps/s 1.5125 KOps/s $\color{#35bf28}+3.32\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1131s 8.9777ms 111.3867 Ops/s 112.0777 Ops/s $\color{#d91a1a}-0.62\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 16.5683ms 14.2965ms 69.9473 Ops/s 68.2571 Ops/s $\color{#35bf28}+2.48\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.1184ms 1.0471ms 955.0068 Ops/s 920.2865 Ops/s $\color{#35bf28}+3.77\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 97.0938ms 6.6323ms 150.7765 Ops/s 114.7923 Ops/s $\textbf{\color{#35bf28}+31.35\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.1078s 16.2273ms 61.6244 Ops/s 69.0238 Ops/s $\textbf{\color{#d91a1a}-10.72\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.3274ms 1.1704ms 854.3947 Ops/s 922.7886 Ops/s $\textbf{\color{#d91a1a}-7.41\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 99.0397ms 6.9938ms 142.9843 Ops/s 140.6466 Ops/s $\color{#35bf28}+1.66\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 16.8387ms 14.7639ms 67.7326 Ops/s 67.0630 Ops/s $\color{#35bf28}+1.00\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.7272ms 1.5041ms 664.8528 Ops/s 636.4512 Ops/s $\color{#35bf28}+4.46\%$

@vmoens vmoens added enhancement New feature or request ciflow/docs tests full docs CI labels Mar 4, 2024
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Mar 4, 2024

No ciflow labels are configured for this repo.
For information on how to enable CIFlow bot see this wiki

@vmoens vmoens merged commit 5ad2436 into main Mar 4, 2024
67 checks passed
@vmoens vmoens deleted the repr_rbs branch March 4, 2024 14:26
vmoens added a commit that referenced this pull request Mar 25, 2024
@vmoens
[Feature] Better repr of RBs (#1991)
8510e47 
(cherry picked from commit 5ad2436)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
ciflow/docs tests full docs CI CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

[Feature Request] ReplayBuffer element display and store None
2 participants
@vmoens @facebook-github-bot