Loop-invariant synthesis is the basis of every program verificationprocedure . Despite the common belief that the design ofheuristics is vital for the effective performance of a verifier, little work has been performed toward obtaining the optimal heuristics for eachinvarant-synthesis tool . This study demonstrates that we can effectively and automatically learn a good heuristic via reinforcement learning for an invariant synthesizer PCSat . PCSat combined with the heuristic learned byreinforcement learning outperforms the state-of-the-art solvers for this task .

Author(s) : Takeshi Tsukada, Hiroshi Unno, Taro Sekiyama, Kohei Suenaga

Links : PDF - Abstract

Code :
Coursera

Keywords : invariant - synthesis - learning - loop - pcsat -

Leave a Reply

Your email address will not be published. Required fields are marked *