Understanding Curriculum Learning in Policy Optimization for Solving Combinatorial Optimization Problems. (arXiv:2202.05423v2 [cs.LG] UPDATED)

Over the recent years, reinforcement learning (RL) starts to show promising
results in tackling combinatorial optimization (CO) problems, in particular
when coupled with curriculum learning to facilitate training. Despite emerging
empirical evidence, theoretical study on why RL helps is still at its early
stage. This paper presents the first systematic study on policy optimization
methods for online CO problems. We show that online CO problems can be
naturally formulated as latent Markov Decision Processes (LMDPs), and prove
convergence bounds on …

arxiv curriculum curriculum learning optimization policy understanding