Off-Policy Actor-Critic with Emphatic Weightings.
Eric GravesEhsan ImaniRaksha KumaraswamyMartha WhitePublished in: J. Mach. Learn. Res. (2023)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- temporal difference
- neuro fuzzy
- policy gradient
- approximate dynamic programming
- gradient method
- policy iteration
- reinforcement learning algorithms
- function approximation
- evaluation function
- average reward
- dynamical systems
- neural network
- dynamic programming
- np hard
- learning algorithm
- multi agent
- model free
- fixed point
- mathematical model
- optimal policy
- optimization problems