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

Anderson Rocha Tavares, Sivasubramanian Anbalagan, Leandro Soriano Marcolino, Luiz Chaimowicz

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.
BibTeX
@inproceedings{tavares2018algorithms,
  author = {Anderson Rocha Tavares and Sivasubramanian Anbalagan and Leandro Soriano Marcolino and Luiz Chaimowicz},
  title = {{Algorithms or Actions? A Study in Large-Scale Reinforcement Learning}},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year = {2018},
  doi = {10.24963/ijcai.2018/377},
}

Loading related content...

Figure