cleanba
CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL
OTHER License
Stars
105
Ecosystems:
Python
Full Changelog: https://github.com/vwxyzjn/cleanba/compare/v1.0.0b2...v1.0.0b3
cleanba
- v1.0.0b2 pre-release (bug fix)
Published by vwxyzjn about 1 year ago
Full Changelog: https://github.com/vwxyzjn/cleanba/compare/v1.0.0b1...v1.0.0b2
cleanba
- v1.0.0b1 pre-release (many refactor)
Published by vwxyzjn about 1 year ago
What's Changed
- Improvement by @vwxyzjn in https://github.com/vwxyzjn/cleanba/pull/2
- fix hts-rl paper link by @ChufanSuki in https://github.com/vwxyzjn/cleanba/pull/3
- Remove the legacy last action rewards script by @vwxyzjn in https://github.com/vwxyzjn/cleanba/pull/7
- add grad accum for ppo + envpool + impala atari wrapper by @51616 in https://github.com/vwxyzjn/cleanba/pull/8
- Add actor threads example by @vwxyzjn in https://github.com/vwxyzjn/cleanba/pull/6
New Contributors
- @vwxyzjn made their first contribution in https://github.com/vwxyzjn/cleanba/pull/2
- @ChufanSuki made their first contribution in https://github.com/vwxyzjn/cleanba/pull/3
- @51616 made their first contribution in https://github.com/vwxyzjn/cleanba/pull/8
Full Changelog: https://github.com/vwxyzjn/cleanba/compare/v0.0.1...v1.0.0b1
cleanba
- Dummy Release
Published by vwxyzjn over 1 year ago