62 search results - page 5 / 13 » Learning and Exploiting Relative Weaknesses of Opponent Agen... |
LAMAS
2005
Springer
15 years 3 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...
CIG
2005
IEEE
15 years 3 months ago
2005
IEEE
Several attempts have been made in the past to construct encoding schemes that allow modularity to emerge in evolving systems, but success is limited. We believe that in order to c...
104
click to vote
ATAL
2011
Springer
13 years 9 months ago
2011
Springer
Researchers in the field of multiagent sequential decision making have commonly used the terms “weakly-coupled” and “loosely-coupled” to qualitatively classify problems i...
AAAI
2007
14 years 11 months ago
2007
In semi-supervised learning, a number of labeled examples are usually required for training an initial weakly useful predictor which is in turn used for exploiting the unlabeled e...
100
click to vote
JMLR
2012
12 years 12 months ago
2012
Many real-world problems are inherently hierarchically structured. The use of this structure in an agent’s policy may well be the key to improved scalability and higher performa...