Learning
by A. Defaweux, T. Lenaerts, S. Maes, K. Tuyls, P. Van Remortel, K. Verbeeck
http://como.vub.ac.be/PoolMembers/tlenaert/file/tlomas.ps
Add To MetaCart
Abstract:
In this paper we address two topics which are currently under investigation in our research lab. The rst concerns the emergence of cooperation in a system with competing agents and how this can be modeled through a system of Reinforcement Learning (RL) agents. Current problems result from the fact that RL systems try to model all agents active in the environment. As a solution we are examining biological niching models and measures in order to reduce the complexity of the agent's learning model. The second topic is closely related to the rst one since it addresses the emergence of cooperating evolving groups through evolutionary transitions.
Citations
| 100 | Niching Methods for Genetic Algorithms – Mahfoud - 1995 |
| 99 | Multiagent Systems – Weiss, Ed - 1999 |
| 62 | Intrinsic Adaptation in a Simple Model for Evolution – Packard - 1989 |
| 50 | Multi-Agent Systems and Societies of Agents – Huhns, Stephens - 1999 |
| 28 | Game theory evolving: A problemcentered introduction to modeling strategic behavior – Gintis - 2000 |
| 22 | Darwinian Dynamics, Evolutionary Transitions in Fitness and Individuality – Michod - 1999 |
| 9 | Coevolutionary Algorithms – Paredis - 1997 |
| 7 | Markov games as a framework for multi-agent reinforcement learning – Litmann - 1994 |
| 1 | Multi Agent Reinforcement Learning in Stochastic Games – Hu, Wellman - 1999 |
