Affordance as general value function: A computational model
This work addresses the challenge of integrating action and perception in robotics and AI by offering a computational model that could enhance autonomous systems, though it appears incremental as it builds on existing GVF literature.
The paper tackles the problem of modeling affordances as long-term predictive summaries by connecting them to general value functions (GVFs) in reinforcement learning, showing that GVFs provide a scalable framework for learning affordances in real-world applications like robotics.
General value functions (GVFs) in the reinforcement learning (RL) literature are long-term predictive summaries of the outcomes of agents following specific policies in the environment. Affordances as perceived action possibilities with specific valence may be cast into predicted policy-relative goodness and modelled as GVFs. A systematic explication of this connection shows that GVFs and especially their deep learning embodiments (1) realize affordance prediction as a form of direct perception, (2) illuminate the fundamental connection between action and perception in affordance, and (3) offer a scalable way to learn affordances using RL methods. Through an extensive review of existing literature on GVF applications and representative affordance research in robotics, we demonstrate that GVFs provide the right framework for learning affordances in real-world applications. In addition, we highlight a few new avenues of research opened up by the perspective of "affordance as GVF", including using GVFs for orchestrating complex behaviors.