Using reinforcement learning to vary the m in GMRES(m).
Lisa PeairsTzu-Yi ChenPublished in: ICCS (2011)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- temporal difference
- reinforcement learning algorithms
- multi agent
- markov decision processes
- autonomous learning
- machine learning
- control problems
- temporal difference learning
- action selection
- continuous state
- reinforcement learning methods
- function approximators
- dynamic programming
- learning algorithm