Correntropy kernel temporal differences for reinforcement learning brain machine interfaces.
Jihye BaeLuis G. Sánchez GiraldoJosé C. PríncipeJoseph T. FrancisPublished in: IJCNN (2014)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- td learning
- reinforcement learning algorithms
- model free
- evaluation function
- monte carlo
- policy evaluation
- action selection
- temporal difference methods
- step size
- supervised learning
- kernel function
- policy iteration
- function approximators
- state space
- feature space
- markov decision processes
- data sets
- multiscale
- machine learning
- support vector machine
- decision trees
- learning algorithm
- neural network