Relative value iteration algorithm with soft state aggregation (Q2705757)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Relative value iteration algorithm with soft state aggregation |
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Relative value iteration algorithm with soft state aggregation |
scientific article |
Statements
1 August 2001
0 references
optimal stochastic control
0 references
dynamic programming
0 references
Markov decision processes
0 references
state aggregation
0 references
compact representation
0 references
value iteration algorithm
0 references
contraction
0 references
Relative value iteration algorithm with soft state aggregation (English)
0 references
A straightforward way to dispel the curse of dimensionality in large stochastic control problems is to replace the lookup table with a generalized function approximator such as state aggregation. The relative value iteration algorithm for average reward Markov decision processes (MDP) with soft state aggregation is investigated. Under a condition of contraction involving a semi-norm, the convergence of the proposed algorithm is proved and an error bound of the approximation is also given.
0 references
