Learning Heuristics for Template-based CEGIS of Loop Invariants with Reinforcement Learning

no code implementations • 16 Jul 2021 • Minchao Wu, Takeshi Tsukada, Hiroshi Unno, Taro Sekiyama, Kohei Suenaga

As a concrete example, we implement the approach on top of PCSat, which is an invariant synthesizer based on template-based CEGIS.

reinforcement-learning Reinforcement Learning (RL)

TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning

no code implementations • NeurIPS 2021 • Minchao Wu, Michael Norrish, Christian Walder, Amir Dezfouli

We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning.

Automated Theorem Proving Deep Reinforcement Learning +2