exploiting structural information that is commonly available in practice. We propose a novel learning algorithm that we call … viable learning policy for structured bandit problems that has asymptotic minimal regret …

Learning. Specifically, our study is framed in the context where a reference discrete optimization problem is given and there …

Simulation-Based Optimization: Parametric Optimization Techniques and Reinforcement Learning introduces the evolving … optimization via temporal differences and Reinforcement Learning: Q-Learning, SARSA, and R-SMART algorithms, and policy search, via … API, Q-P-Learning, actor-critics, and learning automata · A special examination of neural-network-based function …

dynamic programming for discrete states -- Approximate dynamic programming and reinforcement learning for discrete states … -- Numerical dynamic programming for continuous states -- Approximate dynamic programming and reinforcement learning for continuous …