Evolutionary policy iteration under a sampling regime for stochastic combinatorial optimization

Keyphrases

• Evolutionary Policy 100%
• Policy Iteration 100%
• Stochastic Combinatorial Optimization 100%
• Sampling Regime 100%
• Stochastic Optimization Problem 20%
• Discrete Stochastic Optimization 20%
• Policy Selection 20%
• Infinite-horizon Markov Decision Process 20%
• Finite Action Space 20%
• Large Action Space 20%
• Optimal Actions 20%
• Sampling Schedule 20%
• Cost Value 20%
• Optimization Setting 20%

Mathematics

• Stochastics 100%
• Monte Carlo 100%
• Action Space 66%
• Function Value 33%
• Markov Decision Process 33%