1863 search results - page 57 / 373 » Multiagent learning using a variable learning rate |
164
click to vote
ATAL
2011
Springer
14 years 2 months ago
2011
Springer
A key component of any reinforcement learning algorithm is the underlying representation used by the agent. While reinforcement learning (RL) agents have typically relied on hand-...
138
click to vote
SIGIR
2011
ACM
14 years 5 months ago
2011
ACM
The situation in which a choice is made is an important information for recommender systems. Context-aware recommenders take this information into account to make predictions. So ...
123
click to vote
JUCS
2007
15 years 2 months ago
2007
: Competence development programmes are collections of units of learning and learning activities used to increase the overall effective performance of a learner within a certain ta...
109
click to vote
ATAL
2005
Springer
15 years 8 months ago
2005
Springer
Temporal difference (TD) learning methods [22] have become popular reinforcement learning techniques in recent years. TD methods have had some experimental successes and have been...
124
click to vote
ICMLA
2008
15 years 3 months ago
2008
In this work, a new learning paradigm called target selection is proposed, which can be used to test for associations between a single genetic variable and a multidimensional, qua...