Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysis

TL;DR

This paper introduces a Feudal HRL algorithm that autonomously discovers symbolic goal representations through reachability analysis, enabling interpretable, transferable, and data-efficient learning in navigation tasks.

Contribution

It presents a novel developmental mechanism for goal discovery that combines symbolic reachability analysis with hierarchical reinforcement learning.

Findings

Learned goal representations are interpretable and transferable.

The approach improves data efficiency in complex navigation tasks.

The method effectively preserves environment dynamics during goal abstraction.

Abstract

Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning. However, the existing Hierarchical Reinforcement Learning (HRL) approaches relying on symbolic reasoning are often limited as they require a manual goal representation. The challenge in autonomously discovering a symbolic goal representation is that it must preserve critical information, such as the environment dynamics. In this paper, we propose a developmental mechanism for goal discovery via an emergent representation that abstracts (i.e., groups together) sets of environment states that have similar roles in the task. We introduce a Feudal HRL algorithm that concurrently learns both the goal representation and a hierarchical policy. The algorithm uses symbolic reachability analysis for neural networks to approximate the transition relation among sets of states and to refine the goal representation. We evaluate our approach on complex navigation tasks, showing the learned representation is interpretable, transferrable and results in data efficient learning.