Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
guided_search [2018/07/25 00:30]
admin
guided_search [2018/11/06 09:54] (current)
admin
Line 37: Line 37:
  
 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 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
 +
 +https://​arxiv.org/​abs/​1811.00796v1 Automated Theorem Proving in Intuitionistic Propositional Logic by Deep Reinforcement Learning