Exploratory Combinatorial Optimization with Reinforcement Learning.
Thomas D. BarrettWilliam R. ClementsJakob N. FoersterA. I. LvovskyPublished in: CoRR (2019)
Keyphrases
- combinatorial optimization
- reinforcement learning
- combinatorial optimization problems
- metaheuristic
- traveling salesman problem
- simulated annealing
- combinatorial problems
- branch and bound
- optimization problems
- function approximation
- mathematical programming
- branch and bound algorithm
- model free
- state space
- max flow min cut
- reinforcement learning algorithms
- multi agent
- markov decision processes
- quadratic assignment problem
- hard combinatorial optimization problems
- vehicle routing problem
- dynamic programming
- memetic algorithm
- temporal difference
- learning algorithm
- benchmark problems
- tabu search
- graph theory
- search space
- learning classifier systems
- objective function
- neural network