Robustness in Markov Decision Problems with Uncertain Transition Matrices.
Arnab NilimLaurent El GhaouiPublished in: NIPS (2003)
Keyphrases
- markov decision problems
- transition matrices
- linear programming
- state space
- partially observable
- reinforcement learning
- optimal policy
- markov decision processes
- decision theoretic
- decision processes
- policy iteration
- decision making
- transition probabilities
- utility function
- dynamic programming
- expected utility
- queueing networks
- infinite horizon
- linear program
- average cost
- function approximators
- decision problems
- long run
- np hard