Algorithms or Actions? A Study in Large-Scale Reinforcement Learning

Anderson Rocha Tavares, Sivasubramanian Anbalagan, Leandro Soriano Marcolino, Luiz Chaimowicz
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
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
more » ... sent 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.
doi:10.24963/ijcai.2018/377 dblp:conf/ijcai/TavaresAMC18 fatcat:cp6y4p5yhra5pi4fdvmwm3dsq4