Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation.
Christoph DannYishay MansourMehryar MohriAyush SekhariKarthik SridharanPublished in: CoRR (2022)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- mountain car
- dynamic programming
- state action space
- function approximators
- temporal difference learning
- tile coding
- model free
- feature selection
- temporal difference learning algorithms
- reinforcement learning algorithms
- state space
- radial basis function
- learning tasks
- temporal difference methods
- markov decision processes
- neural network
- optimal control
- control problems
- learning algorithm
- learning agent
- reinforcement learning problems
- support vector