Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation.
Ruida ZhouTao LiuMin ChengDileep KalathilP. R. KumarChao TianPublished in: CoRR (2023)
Keyphrases
- function approximation
- natural actor critic
- reinforcement learning
- reinforcement learning problems
- policy gradient methods
- temporal difference
- temporal difference learning
- function approximators
- model free
- reinforcement learning algorithms
- learning tasks
- robot arm
- reinforcement learning methods
- radial basis function
- multi agent
- actor critic
- neural network
- markov decision processes
- support vector
- control problems
- optimal policy
- real valued