akolishchak/hard-attention
Leaning hard attention model by policy gradient with rewards based on active inference.
LuaMIT
Stargazers
- AjayTalatiLondon, UK
- alec-tschantz
- cannadayr
- cuize2018
- DevRossBaidu -> Tencent -> Web3
- Enescigdem
- famishedroverArizona State University
- ffmpbgrnn
- huangpanxxMicrosoft
- KaiKangSDUShandong University
- lhquixotic
- mmmmimicDanmarks Tekniske Universitet
- outlaceChampaign, IL
- pipiman
- ptigasUniversity of Oxford
- qweradfaqwdsfz
- sarosh-quraishiTU Berlin
- SeekPoint
- swdever
- tomekkorbakAnthropic
- Ubasticchina
- wangxiao5791509Anhui University (安徽大学)
- xinw1012Seattle
- yyhTHU