4 papers
Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback
Woohyeon Byeon, Jiwon Jeon, Jeonghye Kim +1
We study multi-domain LLM training in which two models, each stronger in a different domain, co-evolve by tutoring each other through on-policy feedback. Unlike one-way distillatio…
Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
Giseung Park, Hyunyoung Nam, Woohyeon Byeon +2
Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While max-min MORL has emerged as…
Low-Rank Cyclostationarity Predictive Routing Is Almost as Good as Real-Time Data-based Routing
Oriel-Singer, Ilai-Bistritz, Giseung-Park +3
Dynamic shortest-path routing, using real-time traffic data, enables path selection responsive to evolving conditions. Nevertheless, transportation planning tasks such as adaptive…
Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach
Woohyeon Byeon, Giseung Park, Jongseong Chae +2
In this paper, we propose a provably convergent and practical framework for multi-objective reinforcement learning with max-min criterion. From a game-theoretic perspective, we ref…