Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning

Agents that can autonomously navigate the web through a graphical user interface (GUI) using a unified action space (e.g., mouse and keyboard actions) can require very large amounts of domain-specific expert demonstrations to achieve good performance. Low sample efficiency is often exacerbated in sparse-reward and large-action-space environments, such as a web GUI, where only a few actions are relevant in any given situation. In this work, we consider the low-data regime, with limited or no access to expert behavior. To enable sample-efficient learning, we explore the effect of constraining the action space through textitintent-based affordances -- i.e., considering in any situation only the subset of actions that achieve a desired outcome. We propose Code as Generative Affordances (textbftextttCoGA), a method that leverages pre-trained vision-language models (VLMs) to generate code that determines affordable actions through implicit intent-completion functions and using a fully-automated program generation and verification pipeline. These programs are then used in-the-loop of a reinforcement learning agent to return a set of affordances given a pixel observation. By greatly reducing the number of actions that an agent must consider, we demonstrate on a wide range of tasks in the MiniWob++ benchmark that: 1) textttCoGA is orders of magnitude more sample efficient than its RL agent, 2) textttCoGA's programs can generalize within a family of tasks, and 3) textttCoGA performs better or on par compared with behavior cloning when a small number of expert demonstrations is available.