Corpus ID: 70210114

Guiding SMT solvers with Monte Carlo Tree Search and neural networks

@inproceedings{GrahamLengrand2018GuidingSS,
  title={Guiding SMT solvers with Monte Carlo Tree Search and neural networks},
  author={St'ephane Graham-Lengrand and Michael F{\"a}rber},
  year={2018}
}
Monte Carlo Tree Search (MCTS) is a technique to guide search in a large decision space by taking random samples and evaluating their outcome. Frequently, MCTS is employed together with reward heuristics learnt by neural networks. The talk will propose a guidance mechanism for SMT solvers based on a combination of MCTS and neural networks. Machine learning methods gain importance in automated reasoning. A particularly strong trend are neural networks, having produced state-of-the-art results… Expand
1 Citations
On the naturalness of proofs
  • 5
  • PDF

References

SHOWING 1-10 OF 15 REFERENCES
Mastering the game of Go with deep neural networks and tree search
  • 8,414
  • PDF
Chaff: engineering an efficient SAT solver
  • 3,561
  • PDF
The Strategy Challenge in SMT Solving
  • 34
  • PDF
Proofs in conflict-driven theory combination
  • 9
  • PDF
ENIGMA: Efficient Learning-Based Inference Guiding Machine
  • 49
  • PDF
Psyche: A Proof-Search Engine Based on Sequent Calculus with an LCF-Style Architecture
  • 12
  • PDF
Satisfiability Modulo Theories and Assignments
  • 16
  • PDF
CoRR
  • abs/1701.01329,
  • 2017
...
1
2
...