Home /Research /Efficient exploration through active learning for value function approximation in reinforcement learning

LEARNING

Efficient exploration through active learning for value function approximation in reinforcement learning

Takayuki Akiyama, Hirotaka Hachiya, Masashi Sugiyama

Year: 2010
Citations: 20

Keywords

Reinforcement learningComputer scienceBellman equationSampling (signal processing)Artificial intelligenceMachine learningFunction approximationTemporal difference learningFunction (biology)Active learning (machine learning)

Efficient exploration through active learning for value function approximation in reinforcement learning

Keywords

Related papers

Statistical Learning Theory

Artificial intelligence: a modern approach

Applied Nonlinear Control

A new optimizer using particle swarm theory