The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learning

TL;DR

This paper explores how limiting an AI agent's attention to meaningful choices via affordances can improve hierarchical reinforcement learning by addressing the paradox of choice, leading to faster and better decision-making.

Contribution

It introduces an online, model-free method to learn affordances that restrict available options, enhancing hierarchical RL in complex, long-horizon tasks.

Findings

Fewer, meaningful choices can accelerate learning.

Hard versus soft attention impacts data collection and learning.

The paradox of choice affects RL performance.

Abstract

Decision-making AI agents are often faced with two important challenges: the depth of the planning horizon, and the branching factor due to having many choices. Hierarchical reinforcement learning methods aim to solve the first problem, by providing shortcuts that skip over multiple time steps. To cope with the breadth, it is desirable to restrict the agent's attention at each step to a reasonable number of possible choices. The concept of affordances (Gibson, 1977) suggests that only certain actions are feasible in certain states. In this work, we model "affordances" through an attention mechanism that limits the available choices of temporally extended options. We present an online, model-free algorithm to learn affordances that can be used to further learn subgoal options. We investigate the role of hard versus soft attention in training data collection, abstract value learning in long-horizon tasks, and handling a growing number of choices. We identify and empirically illustrate the settings in which the paradox of choice arises, i.e. when having fewer but more meaningful choices improves the learning speed and performance of a reinforcement learning agent.