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

Autor:	Theile, Mirco, Cao, Hongpeng, Caccamo, Marco, Sangiovanni-Vincentelli, Alberto L.
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted at IROS 2024. A video can be found here: https://youtu.be/L6NOdvU7n7s. The code is available at https://github.com/theilem/uavSim
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2403.12856 Zobrazit plný text záznamu View this record from Arxiv