Algorithms or Actions? A Study in Large-Scale Reinforcement Learning
Lists
Only you see this
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...