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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Theile, Mirco, Cao, Hongpeng, Caccamo, Marco, Sangiovanni-Vincentelli, Alberto L.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912170943447040
author Theile, Mirco
Cao, Hongpeng
Caccamo, Marco
Sangiovanni-Vincentelli, Alberto L.
author_facet Theile, Mirco
Cao, Hongpeng
Caccamo, Marco
Sangiovanni-Vincentelli, Alberto L.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12856
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning
Theile, Mirco
Cao, Hongpeng
Caccamo, Marco
Sangiovanni-Vincentelli, Alberto L.
Machine Learning
Robotics
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.
title Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning
topic Machine Learning
Robotics
url https://arxiv.org/abs/2403.12856