Reinforcement Learning for Branch-and-Bound Optimisation Using Retrospective Trajectories.
Christopher W. F. ParsonsonAlexandre LaterreThomas D. BarrettPublished in: AAAI (2023)
Keyphrases
- branch and bound
- reinforcement learning
- lower bound
- branch and bound algorithm
- search algorithm
- optimal solution
- search space
- column generation
- combinatorial optimization
- upper bound
- beam search
- tree search
- randomly generated problems
- genetic algorithm
- branch and bound method
- function approximation
- branch and bound procedure
- model free
- network design problem
- markov decision processes
- tree search algorithm
- optimal policy
- depth first search
- learning algorithm
- reinforcement learning algorithms
- linear programming relaxation
- search strategies
- branch and bound search
- max sat
- partial solutions
- heuristic search
- dynamic programming
- np hard
- metaheuristic
- moving objects
- objective function
- lagrangian heuristic