| J.E. Kittock. Emergent conventions and the structure of multi-agent systems. In L. Nadel and D. Stein, editors, Proc. of the 1993 Complex systems summer school. Santa Fe Institute Studies in the Sciences of Complexity, Addison-Wesley, 1995. |
....has investigated the possibility of using norms, conventions, and social laws in multi agent systems. Examples of the issues investigated include the control of aggression [1] how conventions might emerge within agent societies [7] the role of social structure in the emergence of conventions [5], group behaviour [2] and the reconsideration of commitments [4] In addition, researchers working in philosophy, sociology, and economics have considered similar issues. A good example is the work of Lewis [6] who has made some progress towards a (non formal) theory of normative behaviour. ....
....they can come to exist within an agent society. There are two main approaches: Off line design: In this approach, social laws are designed off line, and hardwired into agents. Examples in the DAI literature include [8, 3, 1] Emergence from within the system: This possibility is investigated by [7, 5], who experiment with a number of techniques by which a convention can emerge from within a group of agents. The first approach will often be simpler to implement, and might present the system designer with a greater degree of control over system functionality. However, there are a number of ....
[Article contains additional citation context not shown here]
J. E. Kittock. Emergent conventions and the structure of multi-agent systems. In Proceedings of the 1993 Santa Fe Institute Complex Systems Summer School, 1993.
....(the market) Most RL algorithms are composed of rules. Shoham Tennenholtz, 1994) discuss a generalisation of RL to MAS called co learning. Co learning involves individual agents learning in an social environment that includes other agents. Co learning agents must adapt to each other. (Kittock, 1995) describes some computational experiments on the emergence of social conventions through co learning. Work of this kind is beginning to explore how MAS can adapt by reinforcement signals. The use of a universally recognised, quantitative representation of value is common to both RL algorithms, ....
Kittock, J. E. (1995). Emergent conventions and the structure of multiagent systems.
....classifier system. Most RL algorithms are composed of rules. Shoham Tennenholtz (1994) discuss a generalisation of RL to MAS called co learning. Co learning involves individual agents learning in a social environment that includes other agents. Co learning agents must adapt to each other. Kittock (1995) describes some computational experiments on the emergence of social conventions through co learning. Work of this kind is beginning to explore how MAS can adapt by reinforcement signals. The use of a universally recognised, scalar quantity form of value is common to both RL algorithms, ....
Kittock, J. E. (1995). Emergent conventions and the structure of multiagent systems.
No context found.
J.E. Kittock. Emergent conventions and the structure of multi-agent systems. In L. Nadel and D. Stein, editors, Proc. of the 1993 Complex systems summer school. Santa Fe Institute Studies in the Sciences of Complexity, Addison-Wesley, 1995.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC