The Termination Critic

TL;DR

This paper introduces a novel approach to learning behavioral abstractions in reinforcement learning by focusing on the termination condition's information-theoretic properties, leading to more meaningful options.

Contribution

It proposes a new algorithm that optimizes option terminations based on compressibility, using an information-theoretic perspective and a critic for the transition model.

Findings

Options learned are non-trivial and meaningful.

The approach improves learning and planning efficiency.

The method offers a new perspective on option termination criteria.

Abstract

In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents. We propose an algorithm that focuses on the termination condition, as opposed to -- as is common -- the policy. The termination condition is usually trained to optimize a control objective: an option ought to terminate if another has better value. We offer a different, information-theoretic perspective, and propose that terminations should focus instead on the compressibility of the option's encoding -- arguably a key reason for using abstractions. To achieve this algorithmically, we leverage the classical options framework, and learn the option transition model as a "critic" for the termination condition. Using this model, we derive gradients that optimize the desired criteria. We show that the resulting options are non-trivial, intuitively meaningful, and useful for learning and planning.