Optimal Policies Search for Sensor Management
Thomas BréhardEmmanuel DuflosPhilippe VanheeghePierre-Arnaud CoquelinPublished in: CoRR (2009)
Keyphrases
- optimal policy
- markov decision processes
- state space
- search algorithm
- finite horizon
- reinforcement learning
- decision problems
- long run
- infinite horizon
- state dependent
- dynamic programming
- decision making
- policy iteration
- search space
- multistage
- sufficient conditions
- data mining
- average reward
- dynamic programming algorithms
- average reward reinforcement learning