Exploratory combinatorial optimization with reinforcement learning

Conference item

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 explore at test time. 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.

Authors: Barrett, TD; Clements, WR; Foerster, JN; Lvovsky, AI

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Association for the Advancement of Artificial Intelligence
• Host title: Proceedings of the AAAI Conference on Artificial Intelligence
• Volume: 34
• Issue: 4
• Publication date: 2020-06-16
• Acceptance date: 2019-11-10
• Event title: Thirty-Fourth AAAI Conference on Artificial Intelligence
• Event location: New York
• Event website: https://aaai.org/Conferences/AAAI-20/
• Event start date: 2020-02-07
• Event end date: 2020-02-12
• DOI: 10.1609/aaai.v34i04.5723
• Language: English
• Keywords: FFR