495 search results - page 70 / 99 » Constructing States for Reinforcement Learning |
121
click to vote
IEAAIE
2004
Springer
15 years 9 months ago
2004
Springer
For flexible interactions between a robot and humans, we address the issue of automatic recognition of human emotions during the interaction such as embarrassment, pleasure, and af...
140
click to vote
LAWEB
2008
IEEE
15 years 10 months ago
2008
IEEE
This paper presents the results of a qualitative research whose objective was to broaden the understanding on the participation of youngsters and adolescents on Internet-based soc...
138
Voted
ICML
2008
IEEE
16 years 4 months ago
2008
IEEE
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
147
click to vote
PKC
2009
Springer
16 years 4 months ago
2009
Springer
In this work, we consider the task of allowing a content provider to enforce complex access control policies on oblivious protocols conducted with anonymous users. As our primary ...
140
click to vote
ICML
2010
IEEE
15 years 5 months ago
2010
IEEE
We present the first temporal-difference learning algorithm for off-policy control with unrestricted linear function approximation whose per-time-step complexity is linear in the ...