Learning Heuristics for Automated Reasoning through Deep Reinforcement Learning

07/20/2018
by   Gil Lederman, et al.
0

We demonstrate how to learn efficient heuristics for automated reasoning algorithms through deep reinforcement learning. We consider search algorithms for quantified Boolean logics, that already can solve formulas of impressive size - up to 100s of thousands of variables. The main challenge is to find a representation which lends to making predictions in a scalable way. The heuristics learned through our approach significantly improve over the handwritten heuristics for several sets of formulas.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset