TY - JOUR
AU - Barrett, Thomas
AU - Clements, William
AU - Foerster, Jakob
AU - Lvovsky, Alex
PY - 2020/04/03
Y2 - 2024/03/02
TI - Exploratory Combinatorial Optimization with Reinforcement Learning
JF - Proceedings of the AAAI Conference on Artificial Intelligence
JA - AAAI
VL - 34
IS - 04
SE - AAAI Technical Track: Machine Learning
DO - 10.1609/aaai.v34i04.5723
UR - https://ojs.aaai.org/index.php/AAAI/article/view/5723
SP - 3243-3250
AB - <p>Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable, reinforcement learning (RL) has shown promise as a framework with which efficient heuristic methods to tackle these problems can be learned. Previous works construct the solution subset incrementally, adding one element at a time, however, the irreversible nature of this approach prevents the agent from revising its earlier decisions, which may be necessary given the complexity of the optimization task. We instead propose that the agent should seek to continuously improve the solution by learning to <em>explore at test time</em>. Our approach of exploratory combinatorial optimization (ECO-DQN) is, in principle, applicable to any combinatorial problem that can be defined on a graph. Experimentally, we show our method to produce state-of-the-art RL performance on the Maximum Cut problem. Moreover, because ECO-DQN can start from any arbitrary configuration, it can be combined with other search methods to further improve performance, which we demonstrate using a simple random search.</p>
ER -