Hierarchical Reinforcement Learning in Multi-Goal Spatial Navigation with Autonomous Mobile Robots
This work addresses navigation challenges for autonomous mobile robots, but it appears incremental as it focuses on evaluating and contrasting existing HRL methods rather than introducing new paradigms.
The paper tackled the problem of complex robotic navigation by comparing hierarchical reinforcement learning (HRL) with traditional RL, finding that HRL outperforms RL in multi-goal spatial navigation tasks through experiments on sub-goal creation and termination functions.
Hierarchical reinforcement learning (HRL) is hypothesized to be able to leverage the inherent hierarchy in learning tasks where traditional reinforcement learning (RL) often fails. In this research, HRL is evaluated and contrasted with traditional RL in complex robotic navigation tasks. We evaluate unique characteristics of HRL, including its ability to create sub-goals and the termination functions. We constructed a number of experiments to test: 1) the differences between RL proximal policy optimization (PPO) and HRL, 2) different ways of creating sub-goals in HRL, 3) manual vs automatic sub-goal creation in HRL, and 4) the effects of the frequency of termination on performance in HRL. These experiments highlight the advantages of HRL over RL and how it achieves these advantages.