137 search results - page 14 / 28 » Space Planning for Online Community |
NIPS
1993
13 years 8 months ago
1993
While exploring to nd better solutions, an agent performing online reinforcement learning (RL) can perform worse than is acceptable. In some cases, exploration might have unsafe, ...
ICRA
2010
IEEE
13 years 6 months ago
2010
IEEE
— Single-query sampling-based motion planners are an efficient class of algorithms widely used today to solve challenging motion planning problems. This paper exposes the common...
ENTER
2006
Springer
13 years 11 months ago
2006
Springer
The complexity and dynamic nature of travelling offers many opportunities for technological support. But printed guidebooks remain the typical companion, despite many weaknesses. ...
LAMAS
2005
Springer
14 years 1 months ago
2005
Springer
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a r...
HT
2000
ACM
13 years 12 months ago
2000
ACM
In August of 1998 I completed the first hypertextual dissertation at Rensselaer Polytechnic Institute. The dissertation was a case study applying methods of rhetorical analysis an...