Monte Carlo Forest Search: UNSAT Solver Synthesis via Reinforcement learning.
Chris CameronJason S. HartfordTaylor LundyTuan TruongAlan MilliganRex ChenKevin Leyton-BrownPublished in: CoRR (2022)
Keyphrases
- monte carlo
- reinforcement learning
- stochastic approximation
- temporal difference
- monte carlo simulation
- game tree search
- markov chain
- tree search
- policy evaluation
- monte carlo tree search
- importance sampling
- search algorithm
- simulation study
- optimal strategy
- adaptive sampling
- state space
- monte carlo method
- markovian decision
- search space
- learning algorithm
- game tree
- temporal difference learning
- search strategy
- function approximation
- search strategies
- matrix inversion
- model free
- light transport
- global illumination
- monte carlo methods
- dynamic programming
- active learning