Principal components analysis of reward prediction errors in a reinforcement learning task.
Thomas D. SambrookJeremy GoslinPublished in: NeuroImage (2016)
Keyphrases
- principal components analysis
- reinforcement learning
- function approximation
- covariance matrix
- state space
- eligibility traces
- model free
- principal components
- text categorisation
- machine learning
- multivariate statistical analysis
- exploratory data analysis
- dimensionality reduction
- markov decision processes
- linear discriminant analysis
- reinforcement learning algorithms
- multi agent
- support vector machine
- learning algorithm
- optimal policy
- optimal control
- dynamic programming
- average reward
- feature extraction
- hand geometry
- temporal difference
- reward function
- reinforcement learning methods
- total reward
- principal component analysis
- knowledge discovery
- data analysis
- upper bound
- training data
- computer vision
- reward shaping