Bringing Fairness to Actor-Critic Reinforcement Learning for Network Utility Optimization.
Jingdi ChenYimeng WangTian LanPublished in: INFOCOM (2021)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- function approximation
- approximate dynamic programming
- policy gradient
- reinforcement learning algorithms
- optimal control
- gradient method
- neuro fuzzy
- natural actor critic
- optimization problems
- multi agent
- dynamic programming
- state space
- temporal difference learning
- machine learning
- np hard
- optimization method
- monte carlo
- model free
- optimization algorithm
- markov decision processes
- policy iteration
- average reward
- utility function
- optimization methods