rl
rl copied to clipboard
Published
20 hours ago •
pytorch
pytorch
[Feature] "fork" start method for mutli-collectors
:link: Helpful Links
:test_tube: See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2024
- :page_facing_up: Preview Python docs built from this PR
Note: Links to docs will display an error until the docs builds have been completed.
:x: 13 New Failures
As of commit dbfbf2bc062e485d7d7940c5ec78394b50e67681 with merge base 4bce3716b8b5465a44759442329ced968b9e53b4 (
NEW FAILURES - The following jobs have failed:
-
Habitat Tests on Linux / tests (3.9, 11.6) / linux-job (gh)
RuntimeError: Command docker exec -t 74dccdd92574e01e65bb8572ab090d25c8f45564597b8dbf10e7e8aced30ccf9 /exec failed with exit code 139 -
Lint / python-source-and-configs / linux-job (gh)
torchrl/collectors/collectors.py:40:1: F401 'torchrl._utils._ProcessNoWarn' imported but unused -
Unit-tests on Linux / tests-cpu (3.10) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Linux / tests-cpu (3.11) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Linux / tests-cpu (3.8) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Linux / tests-cpu (3.9) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Linux / tests-gpu (3.10, 12.1) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Linux / tests-olddeps (3.8, 11.6) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Linux / tests-optdeps (3.10, 12.1) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Linux / tests-stable-gpu (3.10, 11.8) / linux-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on MacOS CPU / tests (3.11) / macos-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on MacOS CPU / tests (3.8) / macos-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False] -
Unit-tests on Windows / unittests-cpu / windows-job (gh)
test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[True-False-False]
This comment was automatically generated by Dr. CI and updates every 15 minutes.
![pytorch-bot[bot] avatar](https://avatars.githubusercontent.com/in/40112?v=4 "Published by a pub.dev verified publisher"){kind=small}
$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests
Total Benchmarks: 91. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}7$.
Expand to view detailed results
| Name | Max | Mean | Ops | Ops on Repo HEAD |
Change |
|---|---|---|---|---|---|
| test_single | 54.2871ms | 54.0431ms | 18.5038 Ops/s | 17.3849 Ops/s | $\textbf{\color{#35bf28}+6.44\%}$ |
| test_sync | 29.8342ms | 29.4905ms | 33.9093 Ops/s | 33.6748 Ops/s | $\color{#35bf28}+0.70\%$ |
| test_async | 51.6210ms | 27.2807ms | 36.6559 Ops/s | 35.9471 Ops/s | $\color{#35bf28}+1.97\%$ |
| test_simple | 0.3865s | 0.3377s | 2.9614 Ops/s | 2.9098 Ops/s | $\color{#35bf28}+1.77\%$ |
| test_transformed | 0.5099s | 0.4685s | 2.1347 Ops/s | 2.1605 Ops/s | $\color{#d91a1a}-1.19\%$ |
| test_serial | 1.2270s | 1.1899s | 0.8404 Ops/s | 0.8253 Ops/s | $\color{#35bf28}+1.83\%$ |
| test_parallel | 1.0825s | 1.0499s | 0.9525 Ops/s | 0.9521 Ops/s | $\color{#35bf28}+0.04\%$ |
| test_step_mdp_speed[True-True-True-True-True] | 0.1404ms | 20.9731μs | 47.6800 KOps/s | 46.9945 KOps/s | $\color{#35bf28}+1.46\%$ |
| test_step_mdp_speed[True-True-True-True-False] | 52.0480μs | 12.7805μs | 78.2440 KOps/s | 77.2475 KOps/s | $\color{#35bf28}+1.29\%$ |
| test_step_mdp_speed[True-True-True-False-True] | 43.6820μs | 12.2038μs | 81.9416 KOps/s | 80.7522 KOps/s | $\color{#35bf28}+1.47\%$ |
| test_step_mdp_speed[True-True-True-False-False] | 34.1040μs | 7.3081μs | 136.8338 KOps/s | 134.4498 KOps/s | $\color{#35bf28}+1.77\%$ |
| test_step_mdp_speed[True-True-False-True-True] | 90.7300μs | 22.2368μs | 44.9706 KOps/s | 44.0352 KOps/s | $\color{#35bf28}+2.12\%$ |
| test_step_mdp_speed[True-True-False-True-False] | 54.9320μs | 13.8372μs | 72.2689 KOps/s | 69.6319 KOps/s | $\color{#35bf28}+3.79\%$ |
| test_step_mdp_speed[True-True-False-False-True] | 39.2430μs | 13.3977μs | 74.6398 KOps/s | 73.0124 KOps/s | $\color{#35bf28}+2.23\%$ |
| test_step_mdp_speed[True-True-False-False-False] | 35.4760μs | 8.5069μs | 117.5512 KOps/s | 113.9689 KOps/s | $\color{#35bf28}+3.14\%$ |
| test_step_mdp_speed[True-False-True-True-True] | 96.4010μs | 23.3889μs | 42.7552 KOps/s | 41.9420 KOps/s | $\color{#35bf28}+1.94\%$ |
| test_step_mdp_speed[True-False-True-True-False] | 51.2760μs | 15.0945μs | 66.2492 KOps/s | 63.7416 KOps/s | $\color{#35bf28}+3.93\%$ |
| test_step_mdp_speed[True-False-True-False-True] | 41.0770μs | 13.4020μs | 74.6159 KOps/s | 73.6936 KOps/s | $\color{#35bf28}+1.25\%$ |
| test_step_mdp_speed[True-False-True-False-False] | 32.3110μs | 8.5000μs | 117.6467 KOps/s | 113.6314 KOps/s | $\color{#35bf28}+3.53\%$ |
| test_step_mdp_speed[True-False-False-True-True] | 51.9470μs | 24.6147μs | 40.6262 KOps/s | 40.1665 KOps/s | $\color{#35bf28}+1.14\%$ |
| test_step_mdp_speed[True-False-False-True-False] | 58.7500μs | 16.1707μs | 61.8402 KOps/s | 59.8413 KOps/s | $\color{#35bf28}+3.34\%$ |
| test_step_mdp_speed[True-False-False-False-True] | 43.0300μs | 14.5043μs | 68.9449 KOps/s | 67.3405 KOps/s | $\color{#35bf28}+2.38\%$ |
| test_step_mdp_speed[True-False-False-False-False] | 32.4310μs | 9.6160μs | 103.9934 KOps/s | 100.2295 KOps/s | $\color{#35bf28}+3.76\%$ |
| test_step_mdp_speed[False-True-True-True-True] | 51.1150μs | 23.5328μs | 42.4939 KOps/s | 41.4055 KOps/s | $\color{#35bf28}+2.63\%$ |
| test_step_mdp_speed[False-True-True-True-False] | 37.7410μs | 15.1326μs | 66.0826 KOps/s | 64.1335 KOps/s | $\color{#35bf28}+3.04\%$ |
| test_step_mdp_speed[False-True-True-False-True] | 80.1700μs | 15.6607μs | 63.8542 KOps/s | 61.9783 KOps/s | $\color{#35bf28}+3.03\%$ |
| test_step_mdp_speed[False-True-True-False-False] | 35.8370μs | 9.7182μs | 102.8994 KOps/s | 99.6656 KOps/s | $\color{#35bf28}+3.24\%$ |
| test_step_mdp_speed[False-True-False-True-True] | 35.4570μs | 24.6628μs | 40.5469 KOps/s | 39.2103 KOps/s | $\color{#35bf28}+3.41\%$ |
| test_step_mdp_speed[False-True-False-True-False] | 50.2940μs | 16.2939μs | 61.3725 KOps/s | 58.8615 KOps/s | $\color{#35bf28}+4.27\%$ |
| test_step_mdp_speed[False-True-False-False-True] | 48.2510μs | 16.6478μs | 60.0680 KOps/s | 58.7680 KOps/s | $\color{#35bf28}+2.21\%$ |
| test_step_mdp_speed[False-True-False-False-False] | 36.7390μs | 10.8105μs | 92.5027 KOps/s | 89.5333 KOps/s | $\color{#35bf28}+3.32\%$ |
| test_step_mdp_speed[False-False-True-True-True] | 66.3940μs | 25.6571μs | 38.9756 KOps/s | 38.0081 KOps/s | $\color{#35bf28}+2.55\%$ |
| test_step_mdp_speed[False-False-True-True-False] | 51.0960μs | 17.4729μs | 57.2314 KOps/s | 55.6140 KOps/s | $\color{#35bf28}+2.91\%$ |
| test_step_mdp_speed[False-False-True-False-True] | 41.5380μs | 16.5176μs | 60.5415 KOps/s | 58.1251 KOps/s | $\color{#35bf28}+4.16\%$ |
| test_step_mdp_speed[False-False-True-False-False] | 32.5910μs | 10.8348μs | 92.2953 KOps/s | 88.9341 KOps/s | $\color{#35bf28}+3.78\%$ |
| test_step_mdp_speed[False-False-False-True-True] | 57.1370μs | 26.5944μs | 37.6019 KOps/s | 36.2431 KOps/s | $\color{#35bf28}+3.75\%$ |
| test_step_mdp_speed[False-False-False-True-False] | 41.8880μs | 18.5289μs | 53.9698 KOps/s | 52.3023 KOps/s | $\color{#35bf28}+3.19\%$ |
| test_step_mdp_speed[False-False-False-False-True] | 70.4120μs | 17.5525μs | 56.9720 KOps/s | 54.6874 KOps/s | $\color{#35bf28}+4.18\%$ |
| test_step_mdp_speed[False-False-False-False-False] | 41.2870μs | 11.8624μs | 84.3000 KOps/s | 80.7410 KOps/s | $\color{#35bf28}+4.41\%$ |
| test_values[generalized_advantage_estimate-True-True] | 9.7670ms | 9.4440ms | 105.8872 Ops/s | 106.6291 Ops/s | $\color{#d91a1a}-0.70\%$ |
| test_values[vec_generalized_advantage_estimate-True-True] | 36.3735ms | 34.9751ms | 28.5918 Ops/s | 30.1779 Ops/s | $\textbf{\color{#d91a1a}-5.26\%}$ |
| test_values[td0_return_estimate-False-False] | 0.2080ms | 0.1647ms | 6.0717 KOps/s | 6.1158 KOps/s | $\color{#d91a1a}-0.72\%$ |
| test_values[td1_return_estimate-False-False] | 23.7583ms | 23.4607ms | 42.6244 Ops/s | 42.7404 Ops/s | $\color{#d91a1a}-0.27\%$ |
| test_values[vec_td1_return_estimate-False-False] | 37.6747ms | 34.9821ms | 28.5860 Ops/s | 30.0533 Ops/s | $\color{#d91a1a}-4.88\%$ |
| test_values[td_lambda_return_estimate-True-False] | 34.2067ms | 33.7877ms | 29.5966 Ops/s | 29.7624 Ops/s | $\color{#d91a1a}-0.56\%$ |
| test_values[vec_td_lambda_return_estimate-True-False] | 36.4543ms | 35.1333ms | 28.4630 Ops/s | 30.2693 Ops/s | $\textbf{\color{#d91a1a}-5.97\%}$ |
| test_gae_speed[generalized_advantage_estimate-False-1-512] | 11.2502ms | 8.3322ms | 120.0165 Ops/s | 122.5160 Ops/s | $\color{#d91a1a}-2.04\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-1-512] | 2.8774ms | 2.0714ms | 482.7629 Ops/s | 503.1707 Ops/s | $\color{#d91a1a}-4.06\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-1-512] | 0.4836ms | 0.3525ms | 2.8365 KOps/s | 2.9167 KOps/s | $\color{#d91a1a}-2.75\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-32-512] | 48.9582ms | 46.9723ms | 21.2892 Ops/s | 25.2964 Ops/s | $\textbf{\color{#d91a1a}-15.84\%}$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-32-512] | 4.8105ms | 3.1344ms | 319.0408 Ops/s | 332.0547 Ops/s | $\color{#d91a1a}-3.92\%$ |
| test_dqn_speed | 1.9118ms | 1.3315ms | 751.0562 Ops/s | 741.4665 Ops/s | $\color{#35bf28}+1.29\%$ |
| test_ddpg_speed | 3.0242ms | 2.6384ms | 379.0148 Ops/s | 372.5697 Ops/s | $\color{#35bf28}+1.73\%$ |
| test_sac_speed | 8.4495ms | 8.1195ms | 123.1597 Ops/s | 122.4417 Ops/s | $\color{#35bf28}+0.59\%$ |
| test_redq_speed | 14.6560ms | 12.9421ms | 77.2671 Ops/s | 75.4862 Ops/s | $\color{#35bf28}+2.36\%$ |
| test_redq_deprec_speed | 14.7084ms | 12.9090ms | 77.4656 Ops/s | 76.2111 Ops/s | $\color{#35bf28}+1.65\%$ |
| test_td3_speed | 8.2923ms | 8.0524ms | 124.1861 Ops/s | 122.2868 Ops/s | $\color{#35bf28}+1.55\%$ |
| test_cql_speed | 0.1059s | 38.4014ms | 26.0407 Ops/s | 26.9781 Ops/s | $\color{#d91a1a}-3.47\%$ |
| test_a2c_speed | 8.9740ms | 7.4016ms | 135.1068 Ops/s | 128.6351 Ops/s | $\textbf{\color{#35bf28}+5.03\%}$ |
| test_ppo_speed | 8.6273ms | 7.6082ms | 131.4374 Ops/s | 127.9711 Ops/s | $\color{#35bf28}+2.71\%$ |
| test_reinforce_speed | 7.3307ms | 6.5102ms | 153.6046 Ops/s | 148.9392 Ops/s | $\color{#35bf28}+3.13\%$ |
| test_iql_speed | 33.2124ms | 32.2200ms | 31.0366 Ops/s | 30.0900 Ops/s | $\color{#35bf28}+3.15\%$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 2.2746ms | 2.1222ms | 471.2086 Ops/s | 464.8577 Ops/s | $\color{#35bf28}+1.37\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 1.0703ms | 0.4916ms | 2.0343 KOps/s | 2.0165 KOps/s | $\color{#35bf28}+0.88\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 0.7364ms | 0.4729ms | 2.1144 KOps/s | 2.0975 KOps/s | $\color{#35bf28}+0.81\%$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 3.7980ms | 2.1768ms | 459.3993 Ops/s | 467.7150 Ops/s | $\color{#d91a1a}-1.78\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 0.7813ms | 0.4875ms | 2.0513 KOps/s | 2.0565 KOps/s | $\color{#d91a1a}-0.25\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 3.4286ms | 0.4645ms | 2.1529 KOps/s | 2.1547 KOps/s | $\color{#d91a1a}-0.08\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] | 1.7760ms | 1.2912ms | 774.5022 Ops/s | 781.3008 Ops/s | $\color{#d91a1a}-0.87\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] | 4.5746ms | 1.2320ms | 811.6946 Ops/s | 827.1845 Ops/s | $\color{#d91a1a}-1.87\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 2.4548ms | 2.2818ms | 438.2528 Ops/s | 448.4233 Ops/s | $\color{#d91a1a}-2.27\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 0.8289ms | 0.6092ms | 1.6416 KOps/s | 1.6458 KOps/s | $\color{#d91a1a}-0.26\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 90.8132ms | 0.6520ms | 1.5338 KOps/s | 1.7135 KOps/s | $\textbf{\color{#d91a1a}-10.49\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 2.8746ms | 2.1550ms | 464.0323 Ops/s | 439.3049 Ops/s | $\textbf{\color{#35bf28}+5.63\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 0.5971ms | 0.4910ms | 2.0368 KOps/s | 1.9936 KOps/s | $\color{#35bf28}+2.17\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 0.6963ms | 0.4709ms | 2.1237 KOps/s | 2.0348 KOps/s | $\color{#35bf28}+4.37\%$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 2.4650ms | 2.1326ms | 468.9097 Ops/s | 451.9874 Ops/s | $\color{#35bf28}+3.74\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 91.4082ms | 0.6077ms | 1.6455 KOps/s | 2.0455 KOps/s | $\textbf{\color{#d91a1a}-19.55\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 0.5983ms | 0.4624ms | 2.1626 KOps/s | 2.1391 KOps/s | $\color{#35bf28}+1.10\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 2.4407ms | 2.2758ms | 439.4043 Ops/s | 436.6678 Ops/s | $\color{#35bf28}+0.63\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 0.8186ms | 0.6108ms | 1.6372 KOps/s | 1.6425 KOps/s | $\color{#d91a1a}-0.32\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 3.8536ms | 0.5886ms | 1.6989 KOps/s | 1.7141 KOps/s | $\color{#d91a1a}-0.89\%$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] | 88.1152ms | 6.9105ms | 144.7074 Ops/s | 138.5479 Ops/s | $\color{#35bf28}+4.45\%$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] | 14.8743ms | 12.0265ms | 83.1497 Ops/s | 83.4823 Ops/s | $\color{#d91a1a}-0.40\%$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] | 1.6668ms | 1.0334ms | 967.7049 Ops/s | 943.7081 Ops/s | $\color{#35bf28}+2.54\%$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] | 87.2916ms | 6.9177ms | 144.5561 Ops/s | 145.7229 Ops/s | $\color{#d91a1a}-0.80\%$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] | 16.8356ms | 13.5305ms | 73.9068 Ops/s | 83.5126 Ops/s | $\textbf{\color{#d91a1a}-11.50\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] | 1.7461ms | 1.0307ms | 970.1833 Ops/s | 960.5441 Ops/s | $\color{#35bf28}+1.00\%$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] | 86.7413ms | 5.6543ms | 176.8570 Ops/s | 179.9119 Ops/s | $\color{#d91a1a}-1.70\%$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] | 92.4519ms | 13.9199ms | 71.8395 Ops/s | 80.8160 Ops/s | $\textbf{\color{#d91a1a}-11.11\%}$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] | 1.7311ms | 1.3448ms | 743.6208 Ops/s | 733.9345 Ops/s | $\color{#35bf28}+1.32\%$ |
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of GPU Benchmark Tests
Total Benchmarks: 94. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}2$.
Expand to view detailed results
| Name | Max | Mean | Ops | Ops on Repo HEAD |
Change |
|---|---|---|---|---|---|
| test_single | 0.1011s | 0.1005s | 9.9518 Ops/s | 9.4268 Ops/s | $\textbf{\color{#35bf28}+5.57\%}$ |
| test_sync | 91.2707ms | 88.2453ms | 11.3320 Ops/s | 11.5001 Ops/s | $\color{#d91a1a}-1.46\%$ |
| test_async | 0.1759s | 88.3969ms | 11.3126 Ops/s | 11.2342 Ops/s | $\color{#35bf28}+0.70\%$ |
| test_single_pixels | 0.1113s | 0.1109s | 9.0204 Ops/s | 9.0006 Ops/s | $\color{#35bf28}+0.22\%$ |
| test_sync_pixels | 67.4512ms | 66.4798ms | 15.0422 Ops/s | 15.1193 Ops/s | $\color{#d91a1a}-0.51\%$ |
| test_async_pixels | 0.1235s | 55.8890ms | 17.8926 Ops/s | 17.6643 Ops/s | $\color{#35bf28}+1.29\%$ |
| test_simple | 0.6515s | 0.6494s | 1.5399 Ops/s | 1.4885 Ops/s | $\color{#35bf28}+3.46\%$ |
| test_transformed | 0.8507s | 0.8492s | 1.1775 Ops/s | 1.1314 Ops/s | $\color{#35bf28}+4.08\%$ |
| test_serial | 2.1114s | 2.0481s | 0.4882 Ops/s | 0.4778 Ops/s | $\color{#35bf28}+2.18\%$ |
| test_parallel | 1.8473s | 1.8031s | 0.5546 Ops/s | 0.5573 Ops/s | $\color{#d91a1a}-0.48\%$ |
| test_step_mdp_speed[True-True-True-True-True] | 96.4740μs | 33.6200μs | 29.7442 KOps/s | 30.8312 KOps/s | $\color{#d91a1a}-3.53\%$ |
| test_step_mdp_speed[True-True-True-True-False] | 43.0320μs | 20.1445μs | 49.6413 KOps/s | 50.9469 KOps/s | $\color{#d91a1a}-2.56\%$ |
| test_step_mdp_speed[True-True-True-False-True] | 33.8210μs | 19.2536μs | 51.9383 KOps/s | 54.2376 KOps/s | $\color{#d91a1a}-4.24\%$ |
| test_step_mdp_speed[True-True-True-False-False] | 28.1510μs | 11.4460μs | 87.3670 KOps/s | 89.1586 KOps/s | $\color{#d91a1a}-2.01\%$ |
| test_step_mdp_speed[True-True-False-True-True] | 58.3320μs | 35.6403μs | 28.0582 KOps/s | 28.5411 KOps/s | $\color{#d91a1a}-1.69\%$ |
| test_step_mdp_speed[True-True-False-True-False] | 45.8820μs | 21.9550μs | 45.5477 KOps/s | 46.4255 KOps/s | $\color{#d91a1a}-1.89\%$ |
| test_step_mdp_speed[True-True-False-False-True] | 36.3910μs | 21.1761μs | 47.2231 KOps/s | 49.0012 KOps/s | $\color{#d91a1a}-3.63\%$ |
| test_step_mdp_speed[True-True-False-False-False] | 27.1010μs | 13.2947μs | 75.2178 KOps/s | 75.7809 KOps/s | $\color{#d91a1a}-0.74\%$ |
| test_step_mdp_speed[True-False-True-True-True] | 56.0530μs | 36.9427μs | 27.0689 KOps/s | 27.5930 KOps/s | $\color{#d91a1a}-1.90\%$ |
| test_step_mdp_speed[True-False-True-True-False] | 47.4420μs | 24.2096μs | 41.3059 KOps/s | 42.4588 KOps/s | $\color{#d91a1a}-2.72\%$ |
| test_step_mdp_speed[True-False-True-False-True] | 46.3320μs | 21.1153μs | 47.3591 KOps/s | 48.9579 KOps/s | $\color{#d91a1a}-3.27\%$ |
| test_step_mdp_speed[True-False-True-False-False] | 29.0220μs | 13.6713μs | 73.1460 KOps/s | 76.8377 KOps/s | $\color{#d91a1a}-4.80\%$ |
| test_step_mdp_speed[True-False-False-True-True] | 56.4630μs | 39.0528μs | 25.6064 KOps/s | 26.4298 KOps/s | $\color{#d91a1a}-3.12\%$ |
| test_step_mdp_speed[True-False-False-True-False] | 40.6710μs | 25.6710μs | 38.9545 KOps/s | 40.4611 KOps/s | $\color{#d91a1a}-3.72\%$ |
| test_step_mdp_speed[True-False-False-False-True] | 43.5720μs | 22.4374μs | 44.5684 KOps/s | 45.2835 KOps/s | $\color{#d91a1a}-1.58\%$ |
| test_step_mdp_speed[True-False-False-False-False] | 39.5820μs | 15.1358μs | 66.0685 KOps/s | 67.7971 KOps/s | $\color{#d91a1a}-2.55\%$ |
| test_step_mdp_speed[False-True-True-True-True] | 55.1520μs | 37.1365μs | 26.9277 KOps/s | 27.7442 KOps/s | $\color{#d91a1a}-2.94\%$ |
| test_step_mdp_speed[False-True-True-True-False] | 41.5520μs | 23.3528μs | 42.8214 KOps/s | 42.9880 KOps/s | $\color{#d91a1a}-0.39\%$ |
| test_step_mdp_speed[False-True-True-False-True] | 40.3010μs | 24.4036μs | 40.9776 KOps/s | 41.7600 KOps/s | $\color{#d91a1a}-1.87\%$ |
| test_step_mdp_speed[False-True-True-False-False] | 41.6810μs | 14.9801μs | 66.7553 KOps/s | 67.0872 KOps/s | $\color{#d91a1a}-0.49\%$ |
| test_step_mdp_speed[False-True-False-True-True] | 62.7520μs | 39.6808μs | 25.2011 KOps/s | 26.3343 KOps/s | $\color{#d91a1a}-4.30\%$ |
| test_step_mdp_speed[False-True-False-True-False] | 52.2820μs | 25.7422μs | 38.8467 KOps/s | 40.1527 KOps/s | $\color{#d91a1a}-3.25\%$ |
| test_step_mdp_speed[False-True-False-False-True] | 51.3220μs | 26.3357μs | 37.9713 KOps/s | 38.5418 KOps/s | $\color{#d91a1a}-1.48\%$ |
| test_step_mdp_speed[False-True-False-False-False] | 36.2320μs | 17.3882μs | 57.5102 KOps/s | 60.0250 KOps/s | $\color{#d91a1a}-4.19\%$ |
| test_step_mdp_speed[False-False-True-True-True] | 65.9430μs | 41.5196μs | 24.0850 KOps/s | 25.2260 KOps/s | $\color{#d91a1a}-4.52\%$ |
| test_step_mdp_speed[False-False-True-True-False] | 45.3020μs | 27.8239μs | 35.9403 KOps/s | 36.8853 KOps/s | $\color{#d91a1a}-2.56\%$ |
| test_step_mdp_speed[False-False-True-False-True] | 48.9320μs | 26.0957μs | 38.3204 KOps/s | 38.4037 KOps/s | $\color{#d91a1a}-0.22\%$ |
| test_step_mdp_speed[False-False-True-False-False] | 42.0310μs | 17.2224μs | 58.0639 KOps/s | 60.0381 KOps/s | $\color{#d91a1a}-3.29\%$ |
| test_step_mdp_speed[False-False-False-True-True] | 65.9230μs | 41.6454μs | 24.0123 KOps/s | 23.9906 KOps/s | $\color{#35bf28}+0.09\%$ |
| test_step_mdp_speed[False-False-False-True-False] | 45.8520μs | 28.6011μs | 34.9637 KOps/s | 34.8313 KOps/s | $\color{#35bf28}+0.38\%$ |
| test_step_mdp_speed[False-False-False-False-True] | 75.1530μs | 27.3101μs | 36.6165 KOps/s | 36.4014 KOps/s | $\color{#35bf28}+0.59\%$ |
| test_step_mdp_speed[False-False-False-False-False] | 39.4210μs | 18.6417μs | 53.6432 KOps/s | 54.4570 KOps/s | $\color{#d91a1a}-1.49\%$ |
| test_values[generalized_advantage_estimate-True-True] | 25.7653ms | 25.1624ms | 39.7418 Ops/s | 41.2570 Ops/s | $\color{#d91a1a}-3.67\%$ |
| test_values[vec_generalized_advantage_estimate-True-True] | 79.9698ms | 3.1552ms | 316.9403 Ops/s | 313.5795 Ops/s | $\color{#35bf28}+1.07\%$ |
| test_values[td0_return_estimate-False-False] | 97.6440μs | 67.3299μs | 14.8522 KOps/s | 15.6251 KOps/s | $\color{#d91a1a}-4.95\%$ |
| test_values[td1_return_estimate-False-False] | 54.9314ms | 53.7123ms | 18.6177 Ops/s | 19.0819 Ops/s | $\color{#d91a1a}-2.43\%$ |
| test_values[vec_td1_return_estimate-False-False] | 2.0753ms | 1.7664ms | 566.1246 Ops/s | 571.3228 Ops/s | $\color{#d91a1a}-0.91\%$ |
| test_values[td_lambda_return_estimate-True-False] | 87.2170ms | 85.3652ms | 11.7144 Ops/s | 11.9500 Ops/s | $\color{#d91a1a}-1.97\%$ |
| test_values[vec_td_lambda_return_estimate-True-False] | 2.1115ms | 1.7513ms | 570.9953 Ops/s | 571.7244 Ops/s | $\color{#d91a1a}-0.13\%$ |
| test_gae_speed[generalized_advantage_estimate-False-1-512] | 24.4180ms | 23.6987ms | 42.1965 Ops/s | 42.4167 Ops/s | $\color{#d91a1a}-0.52\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-1-512] | 0.8745ms | 0.6930ms | 1.4431 KOps/s | 1.4448 KOps/s | $\color{#d91a1a}-0.12\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-1-512] | 0.7070ms | 0.6515ms | 1.5348 KOps/s | 1.5659 KOps/s | $\color{#d91a1a}-1.99\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-32-512] | 1.5022ms | 1.4506ms | 689.3813 Ops/s | 692.2464 Ops/s | $\color{#d91a1a}-0.41\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-32-512] | 0.9600ms | 0.6587ms | 1.5182 KOps/s | 1.5047 KOps/s | $\color{#35bf28}+0.89\%$ |
| test_dqn_speed | 8.2562ms | 1.4369ms | 695.9187 Ops/s | 676.8008 Ops/s | $\color{#35bf28}+2.82\%$ |
| test_ddpg_speed | 2.9647ms | 2.6860ms | 372.3037 Ops/s | 357.7761 Ops/s | $\color{#35bf28}+4.06\%$ |
| test_sac_speed | 8.3743ms | 7.9211ms | 126.2443 Ops/s | 122.1736 Ops/s | $\color{#35bf28}+3.33\%$ |
| test_redq_speed | 11.2463ms | 10.3042ms | 97.0481 Ops/s | 94.3980 Ops/s | $\color{#35bf28}+2.81\%$ |
| test_redq_deprec_speed | 11.5116ms | 10.9699ms | 91.1584 Ops/s | 87.5250 Ops/s | $\color{#35bf28}+4.15\%$ |
| test_td3_speed | 8.0718ms | 7.8587ms | 127.2471 Ops/s | 122.7112 Ops/s | $\color{#35bf28}+3.70\%$ |
| test_cql_speed | 25.5976ms | 24.8281ms | 40.2770 Ops/s | 38.5172 Ops/s | $\color{#35bf28}+4.57\%$ |
| test_a2c_speed | 5.7564ms | 5.5051ms | 181.6505 Ops/s | 173.3668 Ops/s | $\color{#35bf28}+4.78\%$ |
| test_ppo_speed | 7.5775ms | 5.9029ms | 169.4082 Ops/s | 162.9988 Ops/s | $\color{#35bf28}+3.93\%$ |
| test_reinforce_speed | 4.7161ms | 4.4651ms | 223.9594 Ops/s | 212.7428 Ops/s | $\textbf{\color{#35bf28}+5.27\%}$ |
| test_iql_speed | 20.1241ms | 19.4013ms | 51.5431 Ops/s | 49.3363 Ops/s | $\color{#35bf28}+4.47\%$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 3.0067ms | 2.9097ms | 343.6826 Ops/s | 344.4284 Ops/s | $\color{#d91a1a}-0.22\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 1.1359ms | 0.5489ms | 1.8218 KOps/s | 1.5991 KOps/s | $\textbf{\color{#35bf28}+13.92\%}$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 0.7151ms | 0.5255ms | 1.9029 KOps/s | 1.8845 KOps/s | $\color{#35bf28}+0.98\%$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 3.0358ms | 2.8810ms | 347.0966 Ops/s | 341.5535 Ops/s | $\color{#35bf28}+1.62\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 1.2487ms | 0.5387ms | 1.8563 KOps/s | 1.8124 KOps/s | $\color{#35bf28}+2.42\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 0.7206ms | 0.5188ms | 1.9276 KOps/s | 1.9078 KOps/s | $\color{#35bf28}+1.04\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] | 3.9555ms | 1.5256ms | 655.4809 Ops/s | 640.7736 Ops/s | $\color{#35bf28}+2.30\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] | 1.6519ms | 1.4653ms | 682.4329 Ops/s | 677.6706 Ops/s | $\color{#35bf28}+0.70\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 3.2755ms | 3.0188ms | 331.2605 Ops/s | 329.5279 Ops/s | $\color{#35bf28}+0.53\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 0.8640ms | 0.6712ms | 1.4899 KOps/s | 1.4676 KOps/s | $\color{#35bf28}+1.52\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 4.3537ms | 0.6574ms | 1.5211 KOps/s | 1.5148 KOps/s | $\color{#35bf28}+0.42\%$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 2.9980ms | 2.8689ms | 348.5608 Ops/s | 340.9461 Ops/s | $\color{#35bf28}+2.23\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 0.7266ms | 0.5493ms | 1.8205 KOps/s | 1.8032 KOps/s | $\color{#35bf28}+0.96\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 4.2660ms | 0.5320ms | 1.8798 KOps/s | 1.8986 KOps/s | $\color{#d91a1a}-0.99\%$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 3.0656ms | 2.9186ms | 342.6340 Ops/s | 339.5547 Ops/s | $\color{#35bf28}+0.91\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 1.3450ms | 0.5456ms | 1.8328 KOps/s | 1.8290 KOps/s | $\color{#35bf28}+0.21\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 0.6943ms | 0.5222ms | 1.9151 KOps/s | 1.8987 KOps/s | $\color{#35bf28}+0.86\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 3.1369ms | 3.0185ms | 331.2862 Ops/s | 329.0969 Ops/s | $\color{#35bf28}+0.67\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 0.7754ms | 0.6796ms | 1.4715 KOps/s | 1.4710 KOps/s | $\color{#35bf28}+0.03\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 0.1073s | 0.7898ms | 1.2661 KOps/s | 1.5149 KOps/s | $\textbf{\color{#d91a1a}-16.42\%}$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] | 0.1024s | 6.7736ms | 147.6321 Ops/s | 108.7574 Ops/s | $\textbf{\color{#35bf28}+35.74\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] | 16.6977ms | 14.5490ms | 68.7334 Ops/s | 67.0840 Ops/s | $\color{#35bf28}+2.46\%$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] | 2.0490ms | 1.0767ms | 928.7430 Ops/s | 923.0038 Ops/s | $\color{#35bf28}+0.62\%$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] | 0.1038s | 8.6740ms | 115.2864 Ops/s | 144.7352 Ops/s | $\textbf{\color{#d91a1a}-20.35\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] | 16.8384ms | 14.6815ms | 68.1129 Ops/s | 59.2094 Ops/s | $\textbf{\color{#35bf28}+15.04\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] | 2.1683ms | 1.0817ms | 924.4898 Ops/s | 823.0024 Ops/s | $\textbf{\color{#35bf28}+12.33\%}$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] | 0.1053s | 7.2525ms | 137.8826 Ops/s | 137.8913 Ops/s | $-0.01\%$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] | 17.0911ms | 14.8965ms | 67.1299 Ops/s | 65.5654 Ops/s | $\color{#35bf28}+2.39\%$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] | 2.5594ms | 1.4411ms | 693.9110 Ops/s | 656.8176 Ops/s | $\textbf{\color{#35bf28}+5.65\%}$ |