RoMFAC: A Robust Mean-Field Actor-Critic Reinforcement Learning against Adversarial Perturbations on States.
Ziyuan ZhouGuanjun LiuPublished in: CoRR (2022)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- optimal control
- function approximation
- approximate dynamic programming
- reinforcement learning algorithms
- multi agent
- gradient method
- neuro fuzzy
- policy iteration
- model free
- learning algorithm
- dynamic programming
- optimal policy
- supervised learning
- transition probabilities
- markov decision processes
- initial state
- reinforcement learning methods
- rl algorithms
- markov decision problems
- least squares
- state space