Online Control Policy Optimization for Minimizing Map Uncertainty during Exploration.
Robert SimGregory DudekNicholas RoyPublished in: ICRA (2004)
Keyphrases
- control policy
- batch mode
- approximate dynamic programming
- long run
- reinforcement learning
- online learning
- optimization algorithm
- control policies
- global optimization
- optimization process
- robust optimization
- optimization criteria
- maximum a posteriori
- real time
- multi objective
- admission control
- evolutionary search
- balancing exploration and exploitation
- online algorithms
- belief functions
- mathematical programming
- optimization problems
- markov random field