Releases: vwxyzjn/cleanba
Releases · vwxyzjn/cleanba
v1.0.0b3 Refactor PPO
Full Changelog: v1.0.0b2...v1.0.0b3
v1.0.0b2 pre-release (bug fix)
Full Changelog: v1.0.0b1...v1.0.0b2
v1.0.0b1 pre-release (many refactor)
What's Changed
- Improvement by @vwxyzjn in #2
- fix hts-rl paper link by @ChufanSuki in #3
- Remove the legacy last action rewards script by @vwxyzjn in #7
- add grad accum for ppo + envpool + impala atari wrapper by @51616 in #8
- Add actor threads example by @vwxyzjn in #6
New Contributors
- @vwxyzjn made their first contribution in #2
- @ChufanSuki made their first contribution in #3
- @51616 made their first contribution in #8
Full Changelog: v0.0.1...v1.0.0b1
Contributors
vwxyzjn, 51616, and chufanchen