Stabilizing Value Iteration with and without Approximation Errors.
Ali HeydariPublished in: CoRR (2014)
Keyphrases
- markov decision processes
- state space
- approximation algorithms
- heuristic search
- error analysis
- error bounds
- dynamic programming
- neural network
- approximation error
- data mining
- probability distribution
- lower bound
- computational complexity
- multi agent
- search engine
- efficient computation
- belief state
- error propagation
- error detection
- learning algorithm
- approximation methods
- polygonal approximation
- errors occur