Dream-COP: Guiding Algorithm Discovery for Combinatorial Optimization Problems in an Experience World
Dream-COP is introduced, in which a policy agent learns executable policies through dreaming in this experience world to guide a discovery agent in generating and refining COP programs, and policy replay provides feedback on the quality of the programs revealed and the search steps used, to guide policy selection more...
Kuan Xu, Jian-Ming Wang, Ni Zhang et al.
· 0 citations