Sciweavers

77 search results - page 16 / 16
» Value Function Approximation in Reinforcement Learning Using...
Sort
View
CPHYSICS
2006
103views more  CPHYSICS 2006»
13 years 5 months ago
WATERWAVES: wave particles dynamics on a complex triatomic potential
The WATERWAVES program suite performs complex scattering calculations by propagating a wave packet in a complex, full-dimensional potential for non-rotating (J = 0) but vibrating ...
Simone Taioli, Jonathan Tennyson
NIPS
1998
13 years 6 months ago
Finite-Sample Convergence Rates for Q-Learning and Indirect Algorithms
In this paper, we address two issues of long-standing interest in the reinforcement learning literature. First, what kinds of performance guarantees can be made for Q-learning aft...
Michael J. Kearns, Satinder P. Singh