Dimensionality Reduction and Prioritized Exploration for Policy Search.
Marius MemmelPuze LiuDavide TateoJan PetersPublished in: AISTATS (2022)
Keyphrases
- policy search
- dimensionality reduction
- reinforcement learning
- high dimensional
- principal component analysis
- reinforcement learning algorithms
- feature extraction
- continuous action
- continuous state
- dynamic programming
- feature space
- data points
- reward function
- partially observable markov decision processes
- markov decision problems
- principal components
- knowledge base