Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning
This work addresses a specific problem in reinforcement learning for path planning, offering an incremental improvement over existing methods.
The paper tackled the challenge of exploiting environmental symmetries in reinforcement learning for map-based path planning by proposing equivariant ensembles and a regularization term, resulting in improved sample efficiency and performance.
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 equivariant policies and invariant value functions without specialized neural network components, which we term equivariant ensembles. We further add a regularization term for adding inductive bias during training. In a map-based path planning case study, we show how equivariant ensembles and regularization benefit sample efficiency and performance.