Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning

arXiv:2403.12856v1 Announce Type: new
Abstract: In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance. However, ensuring that the deep RL policy and value networks are respectively equivariant and invariant to exploit these symmetries is a substantial challenge. Related works try to design networks that are equivariant and invariant by construction, limiting them to a very restricted library of components, which in turn hampers the expressiveness of the networks. This paper proposes a method to construct …

abstract arxiv challenge cs.lg cs.ro deep rl design efficiency environmental exploit however map networks path performance planning policy regularization reinforcement reinforcement learning robustness type value