On the Speed of Convergence of Value Iteration on Stochastic Shortest-Path Problems.
Blai BonetPublished in: Math. Oper. Res. (2007)
Keyphrases
- shortest path problem
- shortest path
- stochastic approximation
- interval data
- combinatorial optimization problems
- stochastic shortest path
- single source
- learning automata
- policy iteration
- convergence speed
- high speed
- markov decision processes
- multiple objectives
- state space
- monte carlo
- directed graph
- convergence rate
- real time
- directed acyclic graph
- stochastic optimization
- dynamic programming
- reinforcement learning
- heuristic search
- optimal policy
- genetic programming
- least squares
- neural network