68 search results - page 1 / 14 » Feature-Discovering Approximate Value Iteration Methods |
SARA
2005
Springer
13 years 10 months ago
2005
Springer
Sets of features in Markov decision processes can play a critical role ximately representing value and in abstracting the state space. Selection of features is crucial to the succe...
AMC
2007
13 years 5 months ago
2007
In this paper, a boundary value problem for a nonlinear second-order ordinary differential equation is studied. By means of the maximum principle we established the existence and...
ICRA
2009
IEEE
13 years 11 months ago
2009
IEEE
Abstract— Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers...
NN
2010
Springer
12 years 11 months ago
2010
Springer
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
IJCAI
2007
13 years 6 months ago
2007
Recent scaling up of POMDP solvers towards realistic applications is largely due to point-based methods which quickly converge to an approximate solution for medium-sized problems...