Topic
Multi-agent system
About: Multi-agent system is a research topic. Over the lifetime, 27978 publications have been published within this topic receiving 465191 citations. The topic is also known as: multi-agent systems & multiagent system.
Papers published on a yearly basis
Papers
More filters
••
20 Mar 2017TL;DR: This work poses a cooperative ‘image guessing’ game between two agents who communicate in natural language dialog so that Q-BOT can select an unseen image from a lineup of images and shows the emergence of grounded language and communication among ‘visual’ dialog agents with no human supervision.
Abstract: We introduce the first goal-driven training for visual question answering and dialog agents. Specifically, we pose a cooperative ‘image guessing’ game between two agents – Q-BOT and A-BOT– who communicate in natural language dialog so that Q-BOT can select an unseen image from a lineup of images. We use deep reinforcement learning (RL) to learn the policies of these agents end-to-end – from pixels to multi-agent multi-round dialog to game reward.,,We demonstrate two experimental results.,,First, as a ‘sanity check’ demonstration of pure RL (from scratch), we show results on a synthetic world, where the agents communicate in ungrounded vocabularies, i.e., symbols with no pre-specified meanings (X, Y, Z). We find that two bots invent their own communication protocol and start using certain symbols to ask/answer about certain visual attributes (shape/color/style). Thus, we demonstrate the emergence of grounded language and communication among ‘visual’ dialog agents with no human supervision.,,Second, we conduct large-scale real-image experiments on the VisDial dataset [5], where we pretrain on dialog data with supervised learning (SL) and show that the RL finetuned agents significantly outperform supervised pretraining. Interestingly, the RL Q-BOT learns to ask questions that A-BOT is good at, ultimately resulting in more informative dialog and a better team.
297 citations
•
01 Apr 2003
TL;DR: This book demonstrates that Brownian agent models can be successfully applied in many different contexts, ranging from physicochemical pattern formation, to active motion and swarming in biological systems, to self-assembling of networks, evolutionary optimization, urban growth, economic agglomeration and even social systems.
Abstract: "This book lays out a vision for a coherent framework for understanding complex systems'' (from the foreword by J. Doyne Farmer). By developing the genuine idea of Brownian agents, the author combines concepts from informatics, such as multiagent systems, with approaches of statistical many-particle physics. This way, an efficient method for computer simulations of complex systems is developed which is also accessible to analytical investigations and quantitative predictions. The book demonstrates that Brownian agent models can be successfully applied in many different contexts, ranging from physicochemical pattern formation, to active motion and swarming in biological systems, to self-assembling of networks, evolutionary optimization, urban growth, economic agglomeration and even social systems.
297 citations
•
01 Aug 2002TL;DR: Focusing-on settings where side payments are not possible, it is shown that the mechanism design problem is NP-complete for deterministic mechanisms and if the authors allow randomized mechanisms, the mechanisms design problem becomes tractable.
Abstract: The aggregation of conflicting preferences is a central problem in multiagent systems. The key difficulty is that the agents may report their preferences insincerely. Mechanism design is the art of designing the rules of the game so that the agents are motivated to report their preferences truthfully and a (socially) desirable outcome is chosen. We propose an approach where a mechanism is automatically created for the preference aggregation setting at hand. This has several advantages, but the downside is that the mechanism design optimization problem needs to be solved anew each time. Focusing-on settings where side payments are not possible, we show that the mechanism design problem is NP-complete for deterministic mechanisms. This holds both for dominantstrategy implementation and for Bayes-Nash implementation. We then show that if we allow randomized mechanisms, the mechanism design problem becomes tractable. In other words, the coordinator can tackle the computational complexity introduced by its uncertainty the agents face additional uncertainty. This comes at no loss, and in some cases at a gain, in the (social) objective.
296 citations
••
TL;DR: This paper studies a methodology for group coordination and cooperative control of n agents to achieve a target-capturing task in 3D space based on a cyclic pursuit strategy, where agent i simply pursues agent i+1 modulo n.
295 citations
••
TL;DR: In this article, the convergence analysis of a class of distributed constrained non-convex optimization algorithms in multi-agent systems is studied and it is proved that consensus is asymptotically achieved in the network and that the algorithm converges to the set of Karush-Kuhn-Tucker points.
Abstract: We introduce a new framework for the convergence analysis of a class of distributed constrained non-convex optimization algorithms in multi-agent systems. The aim is to search for local minimizers of a non-convex objective function which is supposed to be a sum of local utility functions of the agents. The algorithm under study consists of two steps: a local stochastic gradient descent at each agent and a gossip step that drives the network of agents to a consensus. Under the assumption of decreasing stepsize, it is proved that consensus is asymptotically achieved in the network and that the algorithm converges to the set of Karush-Kuhn-Tucker points. As an important feature, the algorithm does not require the double-stochasticity of the gossip matrices. It is in particular suitable for use in a natural broadcast scenario for which no feedback messages between agents are required. It is proved that our results also holds if the number of communications in the network per unit of time vanishes at moderate speed as time increases, allowing potential savings of the network's energy. Applications to power allocation in wireless ad-hoc networks are discussed. Finally, we provide numerical results which sustain our claims.
294 citations