2 papers
cs.AI2025
Accelerating Task Generalisation with Multi-Level Skill Hierarchies
Thomas P Cannon, Ãzgür Simsek
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-…
cs.LG2024
Hierarchical Orchestra of Policies
Thomas P Cannon, Ãzgür Simsek
Continual reinforcement learning poses a major challenge due to the tendency of agents to experience catastrophic forgetting when learning sequential tasks. In this paper, we intro…