A Geometric Traversal Algorithm for Reward-Uncertain MDPs.
Eunsoo OhKee-Eung KimPublished in: UAI (2011)
Keyphrases
- detection algorithm
- dynamic programming
- reinforcement learning
- optimization algorithm
- preprocessing
- learning algorithm
- computational complexity
- significant improvement
- tree structure
- k means
- neural network
- probabilistic model
- worst case
- segmentation algorithm
- optimal solution
- objective function
- cost function
- np hard
- search space
- data structure
- model based reinforcement learning