Goto

Collaborating Authors

 Education





RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

Neural Information Processing Systems

Visual Reinforcement Learning (Visual RL), coupled with high-dimensional observations, has consistently confronted the long-standing challenge of out-of-distribution generalization.




Rate-Optimal Online Convex Optimization in Adaptive Linear Control

Neural Information Processing Systems

This general framework encapsulates numerous variations of learning in linear control that have been studied extensively in the literature. When the system parameters are known ahead of time and the costs are fixed and known (convex) quadratics, this amounts to the classical "planning"