notesum.ai

Published at October 31

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner

cs.AI
cs.LG

Released Date: October 31, 2024

Authors: Fu-Chieh Chang1, Yu-Ting Lee2, Hui-Ying Shih3, Pei-Yuan Wu4

Aff.: 1MediaTek Research, Taipei, Taiwan; 2Department of Mathematical Sciences, National Chengchi University, Taipei, Taiwan; 3Department of Mathematics, National Tsing Hua University, Hsinchu, Taiwan; 4Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan

Arxiv: http://arxiv.org/abs/2410.23912v1