495 search results - page 27 / 99 » Constructing States for Reinforcement Learning |
136
click to vote
ATAL
2009
Springer
15 years 10 months ago
2009
Springer
Improving the sample efficiency of reinforcement learning algorithms to scale up to larger and more realistic domains is a current research challenge in machine learning. Model-ba...
141
click to vote
ICMLA
2010
15 years 1 months ago
2010
Abstract--In the Relational Reinforcement learning framework, we propose an algorithm that learns an action model allowing to predict the resulting state of each action in any give...
134
click to vote
ATAL
2008
Springer
15 years 6 months ago
2008
Springer
Recent work in transfer learning has succeeded in making reinforcement learning algorithms more efficient by incorporating knowledge from previous tasks. However, such methods typ...
104
click to vote
AAAI
2007
15 years 6 months ago
2007
An Unobservable MDP (UMDP) is a POMDP in which there are no observations. An Only-Costly-Observable MDP (OCOMDP) is a POMDP which extends an UMDP by allowing a particular costly a...
169
click to vote
BROADNETS
2004
IEEE
15 years 8 months ago
2004
IEEE
The scarcity and large fluctuations of link bandwidth in wireless networks have motivated the development of adaptive multimedia services in mobile communication networks, where i...