10 papers
Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think
Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha +18
Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose pro…
Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning
Tung M. Luu, Hwanhee Kim, Younghwan Lee +1
Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL (PbRL) offers a promising alternative by learni…
Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing
Duc Minh Nguyen, Bao-Ngoc Dao, Tung M. Luu +15
Diffusion-based Vision-Language-Action (VLA) policies enable strong generalization in robotic manipulation, but remain sensitive to spurious visual correlations and noisy action ge…
Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning
Thanh Nguyen, Tri Ton, Hongbin Choe +2
Diffusion-based Q-learning has emerged as a powerful paradigm for offline reinforcement learning, but its reliance on multi-step denoising makes both training and inference computa…
Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning
Thanh Nguyen, Tung Luu, Tri Ton +2
Offline reinforcement learning (RL) has garnered significant interest due to its safe and easily scalable paradigm. However, training under this paradigm presents its own challenge…
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…