Probabilistic Networks and Expert Systems
Probabilistic Networks and Expert Systems
Game Theory and Decision Theory in Multi-Agent Systems
Autonomous Agents and Multi-Agent Systems
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
| Hi-index | 0.00 |
Game theory provides a mathematical framework for multiple agent decision making scenarios where the actions of all agents result in consequences for each individual. In scenarios for which it is important for the agents to coordinate to achieve some group-level goal, however, game theory is limited since it does not accommodate a notion of group-level rationality. Conditional game theory is an extension of classical game theory that provides a framework within which to characterize social influence relationships that lead to a social model of the group and, hence, to well-defined notions of both group and individually rational behavior. Building on Shannon information theory, we use the concepts of entropy and mutual information to develop a mathematical concept of the intrinsic ability of the members of an agent-based system to coordinate their behavior.