166 search results - page 29 / 34 » Safe exploration for reinforcement learning |
IBERAMIA
2004
Springer
14 years 2 months ago
2004
Springer
In this paper we describe MRSCL Geometry a collaborative educational activity that explores the use of robotic technology and wirelessly connected Pocket PCs as tools for teaching ...
IDEAL
2004
Springer
14 years 2 months ago
2004
Springer
Recommender systems are widely used to cope with the problem of information overload and, consequently, many recommendation methods have been developed. However, no one technique i...
AOIS
2004
13 years 10 months ago
2004
Recommender systems are widely used to cope with the problem of information overload and, consequently, many recommendation methods have been developed. However, no one technique i...
GECCO
2005
Springer
14 years 2 months ago
2005
Springer
In reinforcement learning problems it has been considered that neither exploitation nor exploration can be pursued exclusively without failing at the task. The optimal balance bet...
ML
2002
ACM
13 years 8 months ago
2002
ACM
Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find profitable actions while t...