Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation.
Junhong ShenLin F. YangPublished in: AAAI (2021)
Keyphrases
- function approximation
- nearest neighbor
- reinforcement learning
- tile coding
- k nearest neighbor
- knn
- radial basis function
- model free
- temporal difference
- high dimensional
- temporal difference learning
- learning tasks
- training set
- temporal difference learning algorithms
- data points
- temporal difference methods
- td learning
- td methods
- exploration exploitation tradeoff
- linear combination
- genetic algorithm
- supervised learning
- function approximators
- state space
- artificial neural networks
- support vector
- multi agent
- learning algorithm
- data mining