A Bayesian Posterior Updating Algorithm in Reinforcement Learning.
Fangzhou XiongZhiyong LiuXu YangBiao SunCharles ChiuHong QiaoPublished in: ICONIP (5) (2017)
Keyphrases
- learning algorithm
- dynamic programming
- reinforcement learning
- cost function
- times faster
- objective function
- theoretical analysis
- k means
- matching algorithm
- machine learning
- computational cost
- computationally efficient
- detection algorithm
- high accuracy
- segmentation algorithm
- optimization algorithm
- improved algorithm
- np hard
- convergence rate
- preprocessing
- optimal solution
- convex hull
- recognition algorithm
- worst case
- monte carlo
- tree structure
- particle swarm optimization
- probabilistic model
- multi objective
- significant improvement
- computational complexity
- genetic algorithm