A Reinforcement Learning Framework for Combinatorial Optimization

The combination of reinforcement learning methods with neural networks has found success on a growing number of large-scale applications, including backgammon move selection, elevator control, and job-shop scheduling. In this work, we modify and generalize the scheduling paradigm used by Zhang and Dietterich to produce a general reinforcement-learning-based framework for combinatorial optimization.

Authors

• Justin A. Boyan Andrew W. Moore

Keywords

No keywords are indexed for this paper.