Goto

Collaborating Authors

 king 3



Appendix for Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess

Neural Information Processing Systems

The synopsis features were hand-designed. Many of them are natural given the rules of chess. These tables also include saliency estimates averaged over five runs. However, it performed very poorly in that competition, winning fewer games than the random bot. The program and underlying algorithm presented in this paper are largely the same as the originals.