Evolutionary Policy Iteration Under a Sampling Regime for Stochastic Combinatorial Optimization.
Lauren HannahWarren B. PowellPublished in: IEEE Trans. Autom. Control. (2010)
Keyphrases
- combinatorial optimization
- policy iteration
- stochastic approximation
- sample path
- markov decision processes
- monte carlo
- model free
- combinatorial optimization problems
- approximate policy iteration
- metaheuristic
- simulated annealing
- optimal policy
- fixed point
- least squares
- traveling salesman problem
- reinforcement learning
- policy evaluation
- temporal difference
- finite state
- genetic algorithm
- average reward
- markov decision process
- optimization problems
- infinite horizon
- mathematical programming
- optimal control
- evolutionary computation
- state space
- lower bound
- convergence rate
- sample size
- linear programming
- markov chain
- dynamic programming
- markov decision problems
- computer vision