Sciweavers

Share
ICML
2003
IEEE

Exploration in Metric State Spaces

12 years 6 months ago
Exploration in Metric State Spaces
We present metric?? , a provably near-optimal algorithm for reinforcement learning in Markov decision processes in which there is a natural metric on the state space that allows the construction of accurate local models. The algorithm is a generalization of the ?? algorithm of Kearns and Singh, and assumes a black box for approximate planning. Unlike the original ?? , metric?? finds a near optimal policy in an amount of time that does not directly depend on the size of the state space, but instead depends on the covering number of the state space. Informally, the covering number is the number of neighborhoods required for accurate local modeling.
Sham Kakade, Michael J. Kearns, John Langford
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2003
Where ICML
Authors Sham Kakade, Michael J. Kearns, John Langford
Comments (0)
books