Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning
This work addresses the challenge of making AI agents more effective at handling real-world, complex user interfaces, though it is incremental in applying hierarchical methods to a specific domain.
The paper tackled the problem of enabling reinforcement learning agents to interact with complex interfaces, specifically simulated Android applications, by using a hierarchical reinforcement learning architecture that decomposes tasks into simple finger gestures and their combinations, resulting in significant performance improvements over non-hierarchical DQN agents.
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.