Curious Hierarchical Actor-Critic Reinforcement Learning.
Frank RöderManfred EppePhuong D. H. NguyenStefan WermterPublished in: ICANN (2) (2020)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- reinforcement learning algorithms
- optimal control
- approximate dynamic programming
- function approximation
- neuro fuzzy
- gradient method
- policy iteration
- markov decision processes
- model free
- policy gradient methods
- dynamic programming
- average reward
- multi agent
- natural actor critic
- linear program
- state space
- control problems
- monte carlo
- step size
- linear programming
- evaluation function
- learning problems
- partially observable
- reinforcement learning methods
- rl algorithms
- supervised learning
- action selection
- control strategy