Understanding Deep Neural Function Approximation in Reinforcement Learning via ε-Greedy Exploration.
Fanghui LiuLuca VianoVolkan CevherPublished in: CoRR (2022)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference
- exploration exploitation tradeoff
- model free
- function approximators
- temporal difference learning
- tile coding
- mountain car
- state action space
- dynamic programming
- temporal difference learning algorithms
- td learning
- radial basis function
- learning algorithm
- neural network
- reinforcement learning algorithms
- feature selection
- learning tasks
- markov decision processes
- action selection
- state space
- reward function
- artificial neural networks
- multi agent
- temporal difference methods
- monte carlo
- search space