Proceedings Article10.1109/ICMAS.1998.699075
The moving target function problem in multi-agent learning
José M. Vidal,Edmund H. Durfee +1 more
- 03 Jul 1998
- pp 317-324
TL;DR: A framework that can be used to model and predict the behavior of MASs with learning agents is described, which uses a difference equation for calculating the progression of an agent's error in its decision function to tell us how the agent is expected to fare in the MAS.
read more
Abstract: We describe a framework that can be used to model and predict the behavior of MASs with learning agents. It uses a difference equation for calculating the progression of an agent's error in its decision function, thereby telling us how the agent is expected to fare in the MAS. The equation relies on parameters which capture the agents' learning abilities (such as its change rate, learning rate and retention rate) as well as relevant aspects of the MAS (such as the impact that agents have on each other). We validate the framework with experimental results using reinforcement learning agents in a market system, as well as by other experimental results gathered from the AI literature.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Cooperative Multi-Agent Learning: The State of the Art
Liviu Panait,Sean Luke +1 more
TL;DR: This survey attempts to draw from multi-agent learning work in a spectrum of areas, including RL, evolutionary computation, game theory, complex systems, agent modeling, and robotics, and finds that this broad view leads to a division of the work into two categories.
Dynamic pricing by software agents
TL;DR: The potential impact of widespread shopbot usage on prices, the price dynamics that may ensue from various mixtures of automated pricing agents, the potential use of machine-learning algorithms to improve profits, and more generally the interplay among learning, optimization, and dynamics in agent-based information economies are studied.
257
An Analysis of Stochastic Game Theory for Multiagent Reinforcement Learning
Michael Bowling,Manuela Veloso +1 more
- 01 Oct 2000
TL;DR: This paper contributes a comprehensive presentation of the relevant techniques for solving stochastic games from both the game theory community and reinforcement learning communities, and examines the assumptions and limitations of these algorithms.
Resource allocation games with changing resource capacities
Aram Galstyan,Shashikiran Kolar,Kristina Lerman +2 more
- 14 Jul 2003
TL;DR: The results indicate that for a certain range of parameters the system as a whole adapts effectively to the changing capacity levels and results in very little under- or over-utilization of the resources.
Congregation Formation in Multiagent Systems
TL;DR: This paper presents a formal model of a congregation and then applies Vidal and Durfee's CLRI framework to the affinity group domain, and shows that if agents are unable to describe congregations to each other, the problem of forming optimal congregations grows exponentially with the number of agents.
References
•Proceedings Article
The dynamics of reinforcement learning in cooperative multiagent systems
Caroline Claus,Craig Boutilier +1 more
- 01 Jul 1998
TL;DR: This work distinguishes reinforcement learners that are unaware of (or ignore) the presence of other agents from those that explicitly attempt to learn the value of joint actions and the strategies of their counterparts, and proposes alternative optimistic exploration strategies that increase the likelihood of convergence to an optimal equilibrium.
•Book
An open agent architecture
Philip R. Cohen,Adam Cheyer,Michelle Wang,Soon Cheol Baeg +3 more
- 01 Oct 1997
TL;DR: The goal of this ongoing project is to develop an open agent architecture and accompanying user interface for networked desktop and handheld machines that support distributed execution of a user’s requests, interoperability of multiple application subsystems, addition of new agents, and incorporation of existing applications.
On the emergence of social conventions: modeling, analysis, and simulations
Yoav Shoham,Moshe Tennenholtz +1 more
TL;DR: This work introduces a simple and natural strategy-selection rule, called highest cumulative reward (HCR), and shows a class of games in which HCR guarantees eventual convergence to a rationally acceptable social convention.
328
The agent architecture of the University of Michigan digital library
Edmund H. Durfee,Daniel L. Kiskis,William P. Birmingham +2 more
- 01 Oct 1997
TL;DR: The software-engineering aspects of the effort (the tools, techniques and experiences gained) are the focus of this paper.
61
Related Papers (5)
Junling Hu,Michael P. Wellman +1 more
- 24 Jul 1998
Richard S. Sutton,Andrew G. Barto +1 more
- 01 Jan 1988