Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sonmez, Yasin, Junnarkar, Neelay, Arcak, Murat
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916360161853440
author Sonmez, Yasin
Junnarkar, Neelay
Arcak, Murat
author_facet Sonmez, Yasin
Junnarkar, Neelay
Arcak, Murat
contents Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry; however, in many real-world environments, the dynamical model exhibits symmetry independent of the reward model. In this paper, we assume only the dynamics exhibit symmetry, extending the scope of problems in reinforcement learning and learning in control theory to which symmetry techniques can be applied. We use Cartan's moving frame method to introduce a technique for learning dynamics that, by construction, exhibit specified symmetries. Numerical experiments demonstrate that the proposed method learns a more accurate dynamical model
format Preprint
id arxiv_https___arxiv_org_abs_2403_19024
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards
Sonmez, Yasin
Junnarkar, Neelay
Arcak, Murat
Machine Learning
Artificial Intelligence
Robotics
Systems and Control
Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry; however, in many real-world environments, the dynamical model exhibits symmetry independent of the reward model. In this paper, we assume only the dynamics exhibit symmetry, extending the scope of problems in reinforcement learning and learning in control theory to which symmetry techniques can be applied. We use Cartan's moving frame method to introduce a technique for learning dynamics that, by construction, exhibit specified symmetries. Numerical experiments demonstrate that the proposed method learns a more accurate dynamical model
title Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards
topic Machine Learning
Artificial Intelligence
Robotics
Systems and Control
url https://arxiv.org/abs/2403.19024