227 search results - page 8 / 46 » Generalized multiagent learning with performance bound |
ATAL
2011
Springer
12 years 9 months ago
2011
Springer
In multi-agent planning environments, action models for each agent must be given as input. However, creating such action models by hand is difficult and time-consuming, because i...
ATAL
2007
Springer
14 years 3 months ago
2007
Springer
It is known that the complexity of the reinforcement learning algorithms, such as Q-learning, may be exponential in the number of environment’s states. It was shown, however, th...
ICML
2007
IEEE
14 years 10 months ago
2007
IEEE
In supervised learning, we commonly assume that training and test data are sampled from the same distribution. However, this assumption can be violated in practice and then standa...
ATAL
2007
Springer
14 years 3 months ago
2007
Springer
Classically, an approach to the multiagent policy learning supposed that the agents, via interactions and/or by using preliminary knowledge about the reward functions of all playe...
ATAL
2004
Springer
14 years 2 months ago
2004
Springer
Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS’s). First we review one motivation of PD theory, as the information-theoretic extens...