Actor-Critic Deep Reinforcement Learning for Dynamic Multichannel Access.
Chen ZhongZiyang LuMustafa Cenk GursoySenem VelipasalarPublished in: CoRR (2018)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- approximate dynamic programming
- reinforcement learning algorithms
- policy gradient
- function approximation
- dynamic environments
- optimal control
- learning algorithm
- policy iteration
- neuro fuzzy
- action selection
- state space
- dynamic programming
- optimal policy
- average reward
- gradient method
- markov decision processes
- control problems
- single agent
- linear programming
- multi agent
- natural actor critic
- policy gradient methods