Technical Note: \cal Q-Learning
Machine Learning
Economic principles of multi-agent systems
Artificial Intelligence - Special issue on economic principles of multi-agent systems
Software agents
Anytime coalition structure generation with worst case guarantees
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Using collective intelligence to route Internet traffic
Proceedings of the 1998 conference on Advances in neural information processing systems II
Designing agent collectives for systems with markovian dynamics
Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 3
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
A Roadmap of Agent Research and Development
Autonomous Agents and Multi-Agent Systems
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Collective Intelligence and Braess' Paradox
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Cues in the environment: a design principle for ambient intelligence
CHI '06 Extended Abstracts on Human Factors in Computing Systems
perCues: trails of persuasion for ambient intelligence
PERSUASIVE'06 Proceedings of the First international conference on Persuasive technology for human well-being
Hi-index | 0.00 |
The "Collective Intelligence" (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided "world" utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional "team games" We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents' ability to learn. The implication is that "learning" is a property only of high-enough dimensional systems.