Mean Actor Critic.
Kavosh AsadiCameron AllenMelrose RoderickAbdel-rahman MohamedGeorge Dimitri KonidarisMichael L. LittmanPublished in: CoRR (2017)
Keyphrases
- actor critic
- reinforcement learning
- approximate dynamic programming
- optimal control
- policy gradient
- temporal difference
- neuro fuzzy
- gradient method
- reinforcement learning algorithms
- policy iteration
- function approximation
- model free
- average reward
- step size
- linear program
- dynamical systems
- markov decision processes
- artificial neural networks