7 citations · 21 across the 18 of their papers we have counts for
5 papers · 1 filter
Hierarchical Orchestra of Policies
Thomas P Cannon, Özgür 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…
Accelerating Task Generalisation with Multi-Level Skill Hierarchies
Thomas P Cannon, Özgür 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-…
Curricula for Learning Robust Policies with Factored State Representations in Changing Environments
Panayiotis Panayiotou, Özgür Şimşek
Robust policies enable reinforcement learning agents to effectively adapt to and operate in unpredictable, dynamic, and ever-changing real-world environments. Factored representati…
Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent
Karolis Jucys, George Adamopoulos, Mehrab Hamidi +7
Understanding the mechanisms behind decisions taken by large foundation models in sequential decision making tasks is critical to ensuring that such systems operate transparently a…
Identifying Optimal Launch Sites of High-Altitude Latex-Balloons using Bayesian Optimisation for the Task of Station-Keeping
Jack Saunders, Sajad Saeedi, Adam Hartshorne +4
Station-keeping tasks for high-altitude balloons show promise in areas such as ecological surveys, atmospheric analysis, and communication relays. However, identifying the optimal…