What can I do here? A Theory of Affordances in Reinforcement Learning

TL;DR

This paper develops a theoretical framework for affordances in reinforcement learning, enabling agents to identify feasible actions based on environmental features, which improves planning efficiency and transition model learning.

Contribution

It introduces a formal theory of affordances for RL agents, demonstrating their benefits for faster planning and more accurate, generalizable transition models.

Findings

Affordances reduce action space complexity, speeding up planning.

Learning affordances improves transition model accuracy and generalization.

Theoretical results support the dual role of affordances in RL.

Abstract

Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term "affordances" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reducing the number of actions available in any given situation. On the other hand, they facilitate more efficient and precise learning of transition models from data, especially when such models require function approximation. We establish these properties through theoretical results as well as illustrative examples. We also propose an approach to learn affordances and use it to estimate transition models that are simpler and generalize better.