Yibo Jacky Zhang

Enhancing Exploration and Exploitation in Hierarchical Reinforcement Learning with Subgoal Graph Learning

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

Goal-conditioned hierarchical reinforcement learning has demonstrated effectiveness in addressing complicated decision-making tasks by providing ''temporal extraction'', which decomposes tasks into smaller and more manageable ''subgoals''. This enables agents to plan over a longer time scale. …