Nonstationary Reinforcement Learning with Linear Function Approximation.
Huozhi ZhouJinglin ChenLav R. VarshneyAshish JagmohanPublished in: CoRR (2020)
Keyphrases
- function approximation
- non stationary
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference
- temporal difference learning
- mountain car
- radial basis function
- learning tasks
- model free
- reinforcement learning problems
- td learning
- temporal difference methods
- neural network
- state space
- artificial neural networks
- machine learning
- optimal policy
- markov decision processes
- least squares
- long run
- feature vectors
- learning algorithm