Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning

TL;DR

This paper presents a hierarchical reinforcement learning approach that enables agents to interact effectively with complex interfaces by decomposing tasks into subtasks, demonstrated on Android device simulations.

Contribution

Introduces a Hierarchical Distributed Deep Reinforcement Learning architecture that learns gesture-based subtasks and their composition for Android interactions, enhancing DQN performance.

Findings

Hierarchical approach improves interaction efficiency with complex interfaces.

The architecture effectively decomposes tasks into manageable subtasks.

Significant performance gains over flat DQN agents.

Abstract

Hierarchical Reinforcement Learning (HRL) allows interactive agents to decompose complex problems into a hierarchy of sub-tasks. Higher-level tasks can invoke the solutions of lower-level tasks as if they were primitive actions. In this work, we study the utility of hierarchical decompositions for learning an appropriate way to interact with a complex interface. Specifically, we train HRL agents that can interface with applications in a simulated Android device. We introduce a Hierarchical Distributed Deep Reinforcement Learning architecture that learns (1) subtasks corresponding to simple finger gestures, and (2) how to combine these gestures to solve several Android tasks. Our approach relies on goal conditioning and can be used more generally to convert any base RL agent into an HRL agent. We use the AndroidEnv environment to evaluate our approach. For the experiments, the HRL agent uses a distributed version of the popular DQN algorithm to train different components of the hierarchy. While the native action space is completely intractable for simple DQN agents, our architecture can be used to establish an effective way to interact with different tasks, significantly improving the performance of the same DQN agent over different levels of abstraction.