Author name: Bodla Krishna Vamshi, Haizhao Yang

Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning

Bodla Krishna Vamshi, Haizhao Yang / April 1, 2026

arXiv:2603.27971v2 Announce Type: replace
Abstract: Recent years have witnessed the widespread adoption of reinforcement learning (RL), from solving real-time games to fine-tuning large language models using human preference data significantly improvi…

cs.LG

Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning

Bodla Krishna Vamshi, Haizhao Yang / March 31, 2026

arXiv:2603.27971v1 Announce Type: new
Abstract: Recent years have witnessed the widespread adoption of reinforcement learning (RL), from solving real-time games to fine-tuning large language models using human preference data significantly improving a…