Rocha Tavares, Anderson and Anbalagan, Sivasubramanian and Soriano Marcolino, Leandro and Chaimowicz, Luiz (2018) Algorithms or Actions? : A Study in Large-Scale Reinforcement Learning. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18) :. International Joint Conferences on Artificial Intelligence, SWE, pp. 2717-2723. ISBN 9780999241127
ijcai_2018.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.
Download (849kB)
Abstract
Large state and action spaces are very challenging to reinforcement learning. However, in many domains there is a set of algorithms available, which estimate the best action given a state. Hence, agents can either directly learn a performance-maximizing mapping from states to actions, or from states to algorithms. We investigate several aspects of this dilemma, showing sufficient conditions for learning over algorithms to outperform over actions for a finite number of training iterations. We present synthetic experiments to further study such systems. Finally, we propose a function approximation approach, demonstrating the effectiveness of learning over algorithms in real-time strategy games.