CDC
2010
IEEE
12 years 12 months ago
2010
IEEE
Abstract-- We consider reinforcement learning, and in particular, the Q-learning algorithm in large state and action spaces. In order to cope with the size of the spaces, a functio...
ICML
2001
IEEE
14 years 5 months ago
2001
IEEE
We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
Residual gradient (RG) was proposed as an alternative to TD(0) for policy evaluation when function approximation is used, but there exists little formal analysis comparing them ex...
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to co...
ICML
2009
IEEE
14 years 5 months ago
2009
IEEE
