Skip to content

Actions: opendilab/DI-engine

algo_test

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
39 workflow runs
39 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

February 20, 2025 07:02 6h 0m 26s
February 20, 2025 06:41 6h 0m 27s
(dcy) redesign avd from reward
algo_test #711: Commit 17a7a71 pushed by Berit-chengyi
February 18, 2025 07:17 6h 0m 24s dev-rlhf-loss
February 18, 2025 07:17 6h 0m 24s
(dcy) redefine adv
algo_test #710: Commit 7bcd64d pushed by Berit-chengyi
February 18, 2025 04:49 6h 1m 44s dev-rlhf-loss
February 18, 2025 04:49 6h 1m 44s
(dcy) rloo and grpo
algo_test #709: Commit 2cbd9fb pushed by Berit-chengyi
February 14, 2025 09:11 6h 0m 27s dev-rlhf-loss
February 14, 2025 09:11 6h 0m 27s
format(dcy): format files
algo_test #708: Commit eba91a1 pushed by Berit-chengyi
February 14, 2025 08:50 2m 49s dev-rlhf-loss
February 14, 2025 08:50 2m 49s
polish(dcy): polish grpo and rloo and test unit
algo_test #707: Commit 71190d4 pushed by Berit-chengyi
February 14, 2025 06:49 6h 0m 28s dev-rlhf-loss
February 14, 2025 06:49 6h 0m 28s
test&implement(dcy): add unit tests for GRPO and RLOO
algo_test #706: Commit 8d34eac pushed by Berit-chengyi
February 13, 2025 13:02 6h 18m 46s dev-rlhf-loss
February 13, 2025 13:02 6h 18m 46s
test&implement(dcy): add unit tests for GRPO and RLOO
algo_test #705: Commit 9cb6ca3 pushed by Berit-chengyi
February 13, 2025 12:52 6h 0m 24s dev-rlhf-loss
February 13, 2025 12:52 6h 0m 24s
feat(rlhf): add unit tests for GRPO and RLOO
algo_test #704: Commit d3f6f3f pushed by Berit-chengyi
February 13, 2025 12:42 6h 0m 31s dev-rlhf-loss
February 13, 2025 12:42 6h 0m 31s
interface(nyz): add naive interface about grpo/rloo
algo_test #703: Commit 2e49437 pushed by PaParaZz1
February 13, 2025 06:43 6h 0m 27s dev-rlhf-loss
February 13, 2025 06:43 6h 0m 27s
interface(nyz): add naive interface about grpo/rloo
algo_test #702: Commit 6965fd3 pushed by PaParaZz1
February 13, 2025 06:36 3m 15s dev-rlhf-loss
February 13, 2025 06:36 3m 15s
test(nyz): polish ppo and add rlhf ppo loss test
algo_test #701: Commit e8ef818 pushed by PaParaZz1
February 13, 2025 06:08 3m 23s dev-rlhf-loss
February 13, 2025 06:08 3m 23s
polish(pu): delete unused enable_fast_timestep argument (#855)
algo_test #700: Commit 64efcb3 pushed by PaParaZz1
January 27, 2025 11:38 6h 0m 24s main
January 27, 2025 11:38 6h 0m 24s
style(nyz): fix flake8 code style (ci skip)
algo_test #699: Commit 3292384 pushed by PaParaZz1
January 27, 2025 06:17 4s main
January 27, 2025 06:17 4s
feature(zjow): add Implicit Q-Learning (#821)
algo_test #698: Commit dae7673 pushed by PaParaZz1
January 27, 2025 03:34 6h 0m 28s main
January 27, 2025 03:34 6h 0m 28s
v0.5.3
algo_test #697: Commit f60b377 pushed by PaParaZz1
December 23, 2024 06:10 6h 0m 25s v0.5.3
December 23, 2024 06:10 6h 0m 25s
feature(pu): add resume_training option to allow the envstep and trai…
algo_test #696: Commit 1f198e9 pushed by PaParaZz1
November 5, 2024 05:16 6h 0m 27s main
November 5, 2024 05:16 6h 0m 27s
feature(whl): add AWR algorithm (#828)
algo_test #695: Commit 3898386 pushed by PaParaZz1
September 26, 2024 01:38 6h 0m 23s main
September 26, 2024 01:38 6h 0m 23s
polish(nyz): polish api doc details
algo_test #694: Commit d88ebe2 pushed by PaParaZz1
July 6, 2024 09:49 6h 0m 26s main
July 6, 2024 09:49 6h 0m 26s
v0.5.2
algo_test #693: Commit b4ab08a pushed by PaParaZz1
June 27, 2024 08:55 6h 0m 25s v0.5.2
June 27, 2024 08:55 6h 0m 25s
polish(zym): optimize ppo continuous act (#801)
algo_test #692: Commit f5fed7c pushed by PaParaZz1
June 13, 2024 00:50 6h 0m 29s main
June 13, 2024 00:50 6h 0m 29s
fix(nyz): fix gtrxl compatibility bug (#796)
algo_test #691: Commit 13a6d45 pushed by PaParaZz1
May 28, 2024 07:24 6h 0m 28s main
May 28, 2024 07:24 6h 0m 28s
fix(nyz): fix unittest and platformtest bug
algo_test #690: Commit fea4b9e pushed by PaParaZz1
May 7, 2024 04:18 6h 0m 26s main
May 7, 2024 04:18 6h 0m 26s
fix(nyz): fix marl nstep td compatibility bug
algo_test #689: Commit c7c3bac pushed by PaParaZz1
April 24, 2024 04:19 6h 0m 45s main
April 24, 2024 04:19 6h 0m 45s