1566 search results - page 81 / 314 » Planning and learning together |
181
click to vote
ICML
2010
IEEE
15 years 4 months ago
2010
IEEE
POMDPs are the models of choice for reinforcement learning (RL) tasks where the environment cannot be observed directly. In many applications we need to learn the POMDP structure ...
151
click to vote
SIGUCCS
2003
ACM
15 years 11 months ago
2003
ACM
As technology becomes more pervasive in our lives, and continues to change rapidly, it is essential for college students to have opportunities to improve their computer abilities ...
142
click to vote
ICML
2005
IEEE
16 years 7 months ago
2005
IEEE
Many biological propositions can be supported by a variety of different types of evidence. It is often useful to collect together large numbers of such propositions, together with...
142
click to vote
C5
2003
IEEE
15 years 11 months ago
2003
IEEE
This paper describes our approach of utilizing a computational environment to apply a learner’s learning process as a first class object. With this approach, the learner’s le...
193
click to vote
ROBOCUP
2007
Springer
16 years 14 days ago
2007
Springer
Abstract. Two main challenges of robot action planning in real domains are uncertain action effects and dynamic environments. In this paper, an instance-based action model is lear...