Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch.
Tianyu ZhangAmin Banitalebi-DehkordiYong ZhangPublished in: CoRR (2022)
Keyphrases
- combinatorial optimization
- reinforcement learning
- traveling salesman problem
- learning algorithm
- learning process
- optimization problems
- combinatorial optimization problems
- evolutionary algorithm
- state space
- learning capabilities
- simulated annealing
- learning tasks
- branch and bound algorithm
- autonomous learning
- search space
- action selection
- model free
- function approximation
- computer vision
- learning problems
- image segmentation
- metaheuristic
- machine learning
- supervised learning
- learning environment