7 search results - page 2 / 2 » TiMDPpoly: An Improved Method for Solving Time-Dependent MDP... |
CORR
2010
Springer
13 years 6 months ago
2010
Springer
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
SIAMNUM
2010
13 years 2 months ago
2010
In this paper, we study the superconvergence property for the discontinuous Galerkin (DG) and the local discontinuous Galerkin (LDG) methods, for solving one-dimensional time depe...