James Hope
James Hope
Home
Posts
Light
Dark
Automatic
reasoning
Improving Language Models Inductive Bias with Q*
Q*, a hybridisation of Q-learning and the pathfinding algorithm A*, has the potential to enhance the inductive bias of a language model in tasks that demand certain types of reasoning. An implementation of Q* is described here https://lnkd.
Jul 10, 10100
3 min read
generativeAI
,
AgenticAI
Cite
×