Hierarchical reinforcement learning for efficent exploration and transfer

Lorenzo Steccanella, Simone Totaro, Damien Allonsius, Anders Jonsson

Student First Author: Yes

Keywords: Reinforcment Learning, Hierarchical Reinforcment Learning, Transfer Learning, Sparse Reward Domains

Abstract: Sparse-reward domains are challenging for reinforcement learning algorithms since significant exploration is needed before encountering reward for the first time. Hierarchical reinforcement learning can facilitate exploration by reducing the number of decisions necessary before obtaining a reward. In this paper, we present a novel hierarchical reinforcement learning framework based on the compression of an invariant state space that is common to a range of tasks. The algorithm introduces subtasks which consist in moving between the state partitions induced by the compression. Results indicate that the algorithm can successfully solve complex sparse-reward domains, and transfer knowledge to solve new, previously unseen tasks more quickly.

TL;DR: Learning through a hierarchy of options can provide fast convergence rates on sparse reward settings and transfer of knowledge capabilities