samuki/reinforce-joey
This is a fork of the awesome Joey-NMT with Reinforcement Learning algorithms like Policy Gradient, MRT and Advantage Actor Critic.
PythonApache-2.0
Stargazers
- 787264137
- APodolskiyMoscow
- arendu-zzBaltimore
- bricksdontUniversity of Zurich
- BrightXiaoHanIfun Game
- chenming-wuTsinghua University
- cielaFukushima
- dsj96
- ElliottYanZhejiang University
- gojitejiNAIST NLP Lab & mocomoco inc.
- he0x
- imr555Neovotech
- juliakreutzerMontreal, Canada
- kushalarora@mila-iqia @rllabmcgill
- kyoto7250Japan
- liamcripwellNuMind
- marvosyntacticalHeidelberg University
- michelleqyhqyh
- ruoyuGaoAWS
- urchadeParis
- woog2eeSeoul, Korea
- xkiantebHarvard University
- yv
- zhaoguangxiangPeking University
- zhengzx-nlpShanghai, China
- ZJYCPShanghai University