Approximate Dynamic Programming based on Projection onto the (min, +) subsemimodule.
Chandrashekar LakshminarayananShalabh BhatnagarPublished in: CoRR (2014)
Keyphrases
- approximate dynamic programming
- linear program
- dynamic programming
- reinforcement learning
- stochastic dynamic programming
- factored mdps
- step size
- convex sets
- linear programming
- machine learning
- multiresolution
- search algorithm
- image compression
- markov chain
- multistage
- optimal solution
- multiple agents
- average cost
- markov decision process
- policy iteration