Anderson Acceleration for Reinforcement Learning.
Matthieu GeistBruno ScherrerPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- state space
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- model free
- robotic control
- machine learning
- control problems
- markov decision processes
- learning problems
- action selection
- optimal control
- data sets
- dynamic programming
- reward function
- multi agent
- learning capabilities
- case study
- databases