Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning 事件

Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning arXiv:2605.26012v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intrinsically low-dimensional. In this work, we present a simple yet effective representation-level prior that inserts a fixed orthonormal projection to constrain encoder features to a