4035 search results - page 334 / 807 » Useless Actions Are Useful |
180
click to vote
TVCG
2012
13 years 9 months ago
2012
—This paper describes a new method to explore and discover within a large data set. We apply techniques from preference elicitation to automatically identify data elements that a...
172
click to vote
JIT
2005
Springer
16 years 7 days ago
2005
Springer
Dynamic AOP has been identified as a useful technique to implement an auto-adaptive framework. To supplement this policies based upon EventCondition-Action rules are used to specif...
183
click to vote
IROS
2009
IEEE
16 years 1 months ago
2009
IEEE
— In multi-robot systems, task allocation and coordination are two fundamental problems that share high synergy. Although multi-robot architectures typically separate them into d...
174
click to vote
IJCNN
2007
IEEE
16 years 1 months ago
2007
IEEE
- This paper presents an optimal energy control scheme for a grid independent photovoltaic (PV) solar system consisting of a PV array, battery energy storage, and time varying load...
160
click to vote
ECML
2004
Springer
16 years 4 days ago
2004
Springer
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....