A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalentsby Kaiwen Wang, Dawen Liang,…
From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verificationby Fei Wang, Chao Shang,…
Finite-Time Error Analysis of Soft Q-Learning: Switching System Approachby Narim Jeong, Donghwan LeeFirst submitted to…
FeatAug: Automatic Feature Augmentation From One-to-Many Relationship Tablesby Danrui Qi, Weiling Zheng, Jiannan WangFirst submitted…
Distributional Successor Features Enable Zero-Shot Policy Optimizationby Chuning Zhu, Xinqi Wang, Tyler Han, Simon S.…
Pre-Trained Model Recommendation for Downstream Fine-tuningby Jiameng Bai, Sai Wu, Jie Song, Junbo Zhao, Gang…
Towards Robust Out-of-Distribution Generalization Bounds via Sharpnessby Yingtian Zou, Kenji Kawaguchi, Yingnan Liu, Jiashuo Liu,…
DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learningby Xuefeng Wang, Henglin Pu,…
On the Diminishing Returns of Width for Continual Learningby Etash Guha, Vihan LakshmanFirst submitted to…
What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of…