Reinforcement Learning: Connections, Surprises, and Challenge.
Andrew G. BartoPublished in: AI Mag. (2019)
Keyphrases
- reinforcement learning
- optimal policy
- reinforcement learning algorithms
- function approximation
- learning algorithm
- neural network
- fitted q iteration
- policy search
- control problems
- markov decision processes
- learning process
- machine learning
- state space
- active learning
- multi agent
- optimal control
- multiscale
- clustering algorithm
- multi agent reinforcement learning
- robotic control
- data sets