Optimism in Reinforcement Learning with Generalized Linear Function Approximation.
Yining WangRuosong WangSimon Shaolei DuAkshay KrishnamurthyPublished in: ICLR (2021)
Keyphrases
- function approximation
- generalized linear
- reinforcement learning
- discriminant analysis
- regression model
- temporal difference
- function approximators
- model free
- temporal difference learning
- autoregressive
- radial basis function
- learning tasks
- machine learning
- reinforcement learning algorithms
- state space
- policy gradient
- neural network
- image processing
- learning algorithm
- data sets
- markov decision processes
- learning experience
- maximum likelihood
- exponential family
- image segmentation
- policy evaluation
- temporal difference methods