Specification-Guided Reinforcement Learning

Communications of the ACM 2026

View at publisher
Authors: Rajeev Alur A, Suguman Bansal, Osbert Bastani, Kishor Jothimurugan
DOI: 10.1145/3744706
Cited by: 0
References: 14

Abstract

A tutorial-style introduction to recent research on using logical specifications to encode RL tasks illustrates theoretical limitations and practical solutions.

Fields of Study & Subjects

Reinforcement Learning in Robotics AI-based Problem Solving and Planning Logic Reasoning and Knowledge

Publication details

Journal / source
Communications of the ACM
Volume
69
Issue
2
Pages
80–87
Publication date
28 January 2026
Language
EN