mlsanityData to 14 Oct 2026

Answer-Set-Programming-based Abstractions for Reinforcement Learning

arXiv 2605.31444 ↗First posted 29 May 2026cs.AI cs.LOcited by 0

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

Reinforcement Learning (RL) enables autonomous agents to learn policies from experience, but realistic problems often involve enormous state spaces, making learning and generalisation challenging. Abstraction and approximation are therefore essential. Relational Reinforcement Learning (RRL) offers a way to reason about objects and their relations, and the CARCASS framework by Martijn van Otterlo demonstrates how logical representations can model Markov Decision Processes (MDPs) in first-order domains. Originally implemented in Prolog, CARCASS leverages domain knowledge to create powerful abstractions. We explore Answer-Set Programming (ASP), which is a rich and, contrary to Prolog, fully declarative modelling language, to realise CARCASS abstractions. We evaluate our ASP-based implementation in case studies of two domains, viz. Blocks World and Minigrid. Our results indicate that CARCASS with ASP provides a promising approach to constructing abstractions for RL, especially when domain knowledge is available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 3 of its 25 references that are in the map. First posted on arXiv 29 May 2026.

Builds on

3 of 25 references.

References · 3

  1. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  2. 2019ASP-Core-2 Input Language Formatcited by 77
  3. 2017Answer Set Programming for Non-Stationary Markov Decision Processescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents
  2. 2025Human-Allied Relational Reinforcement Learning
  3. 2026From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systems
  4. 2024Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning
  5. 2026ASP-Bench: From Natural Language to Logic Programs
  6. 2024Programmatic Reinforcement Learning: Navigating Gridworlds
  7. 2026Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
  8. 2025Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions