An Introduction to MultiAgent Systems.

In the Hamadryas baboon, males are substantially larger than females. A troop of baboons is subdivided into a number of ‘one-male groups’, consisting of one adult male and one or more females with their young. The male prevents any of ‘his’ females from moving too far from him. Kummer (1971) performed the following experiment. Two males, A and B, previously unknown to each other, were placed in a large enclosure. Male A was free to move about the enclosure, but male B was shut in a small cage, from which he could observe A but not interfere. A female, unknown to both males, was then placed in the enclosure. Within 20 minutes male A had persuaded the female to accept his ownership. Male B was then released into the open enclosure. Instead of challenging male A , B avoided any contact, accepting A’s ownership.

Evolution and the Theory of Games

The Art and Science of Negotiation

The key challenge in multiagent learning is learning a best response to the behaviour of other agents, which may be non-stationary: if the other agents adapt their strategy as well, the learning target moves. Disparate streams of research have approached non-stationarity from several angles, which make a variety of implicit assumptions that make it hard to keep an overview of the state of the art and to validate the innovation and significance of new works. This survey presents a coherent overview of work that addresses opponent-induced non-stationarity with tools from game theory, reinforcement learning and multi-armed bandits. Further, we reflect on the principle approaches how algorithms model and cope with this non-stationarity, arriving at a new framework and five categories (in increasing order of sophistication): ignore, forget, respond to target models, learn models, and theory of mind. A wide range of state-of-the-art algorithms is classified into a taxonomy, using these categories and key characteristics of the environment (e.g., observability) and adaptation behaviour of the opponents (e.g., smooth, abrupt). To clarify even further we present illustrative variations of one domain, contrasting the strengths and limitations of each category. Finally, we discuss in which environments the different approaches yield most merit, and point to promising avenues of future research.

A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity

http://ii.tudelft.nl/sites/default/files/aij-anac2011-pub_0.pdf

Evaluating practical negotiating agents: Results and analysis of the 2011 international competition

In multi-issue automated negotiation against unknown opponents, a key part of effective negotiation is the choice of concession strategy. In this paper, we develop a principled concession strategy, based on Gaussian processes predicting the opponent's future behaviour. We then use this to set the agent's concession rate dynamically during a single negotiation session. We analyse the performance of our strategy and show that it outperforms the state-of-the-art negotiating agents from the 2010 Automated Negotiating Agents Competition, in both a tournament setting and in self-play, across a variety of negotiation domains.

Using Gaussian processes to optimise concession in complex negotiations against unknown opponents

We describe the strategy used by our agent, IAMhaggler, which finished in third place in the 2010 Automated Negotiating Agent Competition. It uses a concession strategy to determine the utility level at which to make offers. This concession strategy uses a principled approach which considers the offers made by the opponent. It then uses a Pareto-search algorithm combined with Bayesian learning in order to generate a multi-issue offer with a specific utility as given by its concession strategy.

/pdf/iamhaggler-a-negotiation-agent-for-complex-environments-4vcvxnkjzf.pdf

IAMhaggler: A Negotiation Agent for Complex Environments

We propose a novel strategy to enable autonomous agents to negotiate concurrently with multiple, unknown opponents in real-time, over complex multi-issue domains. We formalise our strategy as an optimisation problem, in which decisions are based on probabilistic information about the opponents' strategies acquired during negotiation. In doing so, we develop the first principled approach that enables the coordination of multiple, concurrent negotiation threads for practical negotiation settings. Furthermore, we validate our strategy using the agents and domains developed for the International Automated Negotiating Agents Competition (ANAC), and we benchmark our strategy against the state-of-the-art. We find that our approach significantly outperforms existing approaches, and this difference improves even further as the number of available negotiation opponents and the complexity of the negotiation domain increases.

/pdf/negotiating-concurrently-with-unknown-opponents-in-complex-44vc8ndyun.pdf

Negotiating concurrently with unknown opponents in complex, real-time domains

The third Automated Negotiating Agents Competition (ANAC 2012) was held at the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2012, Valencia, Spain) ANAC is an international competition that aims to encourage research into bilateral, multi-issue negotiation, by providing a platform in which strategies developed independently by different research teams can be tried and compared against each other, in a real-time competition In the 2012 edition, we received 17 entries from 9 different universities worldwide, out of which 8 were selected for the final round This chapter aims to provide a broad description of the competition set-up (especially highlighting the changes from previous editions), the preference domains and the strategies submitted, as well as the results from both the qualifying and final rounds

Colin R. Williams

Papers

Evaluating practical negotiating agents: Results and analysis of the 2011 international competition

Using Gaussian processes to optimise concession in complex negotiations against unknown opponents

IAMhaggler: A Negotiation Agent for Complex Environments

Negotiating concurrently with unknown opponents in complex, real-time domains

An Overview of the Results and Insights from the Third Automated Negotiating Agents Competition (ANAC2012)