Accelerating Task Generalisation with Multi-Level Skill Hierarchies
This addresses the problem of task generalization in AI for reinforcement learning researchers, with incremental improvements in hierarchical methods.
The paper tackles the challenge of creating reinforcement learning agents that generalize to new tasks by introducing Fracture Cluster Options (FraCOs), a multi-level hierarchical method that achieves state-of-the-art performance, showing higher in-distribution and out-of-distribution results than competitors.
Creating reinforcement learning agents that generalise effectively to new tasks is a key challenge in AI research. This paper introduces Fracture Cluster Options (FraCOs), a multi-level hierarchical reinforcement learning method that achieves state-of-the-art performance on difficult generalisation tasks. FraCOs identifies patterns in agent behaviour and forms options based on the expected future usefulness of those patterns, enabling rapid adaptation to new tasks. In tabular settings, FraCOs demonstrates effective transfer and improves performance as it grows in hierarchical depth. We evaluate FraCOs against state-of-the-art deep reinforcement learning algorithms in several complex procedurally generated environments. Our results show that FraCOs achieves higher in-distribution and out-of-distribution performance than competitors.