Towards an Interpretable Hierarchical Agent Framework using Semantic Goals

TL;DR

This paper presents an interpretable hierarchical reinforcement learning framework that combines planning and semantic goals, improving long-horizon task solving and human interaction in robotic manipulation.

Contribution

It introduces a semantic goal space for hierarchical RL, reducing human effort and enhancing interpretability and performance in robotic tasks.

Findings

Outperforms other methods in block manipulation tasks

Semantic goals improve interpretability and supervision

Reduces need for complex reward engineering

Abstract

Learning to solve long horizon temporally extended tasks with reinforcement learning has been a challenge for several years now. We believe that it is important to leverage both the hierarchical structure of complex tasks and to use expert supervision whenever possible to solve such tasks. This work introduces an interpretable hierarchical agent framework by combining planning and semantic goal directed reinforcement learning. We assume access to certain spatial and haptic predicates and construct a simple and powerful semantic goal space. These semantic goal representations are more interpretable, making expert supervision and intervention easier. They also eliminate the need to write complex, dense reward functions thereby reducing human engineering effort. We evaluate our framework on a robotic block manipulation task and show that it performs better than other methods, including both sparse and dense reward functions. We also suggest some next steps and discuss how this framework makes interaction and collaboration with humans easier.