Neural Combinatorial Optimization with Reinforcement Learning.
Irwan BelloHieu PhamQuoc V. LeMohammad NorouziSamy BengioPublished in: CoRR (2016)
Keyphrases
- combinatorial optimization
- reinforcement learning
- fitted q iteration
- combinatorial optimization problems
- metaheuristic
- simulated annealing
- network architecture
- branch and bound
- traveling salesman problem
- optimization problems
- neural network
- branch and bound algorithm
- mathematical programming
- combinatorial problems
- function approximation
- sensory inputs
- hard combinatorial optimization problems
- model free
- learning algorithm
- optimal policy
- state space
- multi agent
- quadratic assignment problem
- tabu search
- machine learning
- exact algorithms
- markov decision processes
- genetic algorithm
- action selection
- path relinking