4 papers · 1 filter
Policy Learning from Large Vision-Language Model Feedback without Reward Modeling
Tung M. Luu, Donghoon Lee, Younghwan Lee +1
Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consum…
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models
Tung Minh Luu, Younghwan Lee, Donghoon Lee +3
Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from…
Sample Efficient Reinforcement Learning via Large Vision Language Model Distillation
Donghoon Lee, Tung M. Luu, Younghwan Lee +1
Recent research highlights the potential of multimodal foundation models in tackling complex decision-making challenges. However, their large parameters make real-world deployment…
Reward Generation via Large Vision-Language Model in Offline Reinforcement Learning
Younghwan Lee, Tung M. Luu, Donghoon Lee +1
In offline reinforcement learning (RL), learning from fixed datasets presents a promising solution for domains where real-time interaction with the environment is expensive or risk…