arxivst stuff from arxiv that you should probably bookmark

Stochastic Constraint Programming as Reinforcement Learning

Abstract · Apr 24, 2017 12:44 ·

constraint programming uncertainty problems reinforcement modelling stochastic scp cs-ai

Arxiv Abstract

  • Steven Prestwich
  • Roberto Rossi
  • Armagan Tarim

Stochastic Constraint Programming (SCP) is an extension of Constraint Programming (CP) used for modelling and solving problems involving constraints and uncertainty. SCP inherits excellent modelling abilities and filtering algorithms from CP, but so far it has not been applied to large problems. Reinforcement Learning (RL) extends Dynamic Programming to large stochastic problems, but is problem-specific and has no generic solvers. We propose a hybrid combining the scalability of RL with the modelling and constraint filtering methods of CP. We implement a prototype in a CP system and demonstrate its usefulness on SCP problems.

Read the paper (pdf) »