An adequate formulation of collective intentionality is crucial for understanding group activity and for modeling the mental state of participants in such activities. Although work on collective intentionality in philosophy, artificial intelligence, and cognitive science has many points of agreement, several key issues remain under debate. This paper argues that the dynamics of intention—in par...

In the setting of the two-user broadcast channel, recent work by Maddah-Ali and Tse has shown that knowledge of prior channel state information at the transmitter (CSIT) can be useful, even in the absence of any knowledge of current CSIT. Very recent work by Kobayashi et al., Yang et al., and Gou and Jafar, extended this to the case where, instead of no current CSIT knowledge, the transmitter h...

The training of teams in highly dynamic, multi-agent virtual worlds places a heavy demand on an instructor. We address the instructor's problem with the PuppetMaster. The PuppetMaster manages a network of monitors that report on the activities in the simulation in order to provide the instructor with an interpretation and situation-speci c analysis of student behavior. The approach used to mode...

Intentions have been widely studied in AI, both in the context of decision-making within individual agents and in multiagent systems. Work on intentions in multi-agent systems has focused on joint intention models, which characterise the mental state of agents with a shared goal engaged in teamwork. In the absence of shared goals, however, intentions play another crucial role in multi-agent act...

We describe a general mechanism for adaptation in multiagent systems in which agents modify their behavior based on their memory of past events. These behavior changes can be elicited by environmental dynamics or arise as response to the actions of other agents. The agents use memory to estimate the global state of the system from individual observations and adjust their actions accordingly. We...

In realistic multiagent systems, learning on the basis of complete state information is not feasible. We introduce adaptive state focus Q-learning, a class of methods derived from Qlearning that start learning with only the state information that is strictly necessary for a single agent to perform the task, and that monitor the convergence of learning. If lack of convergence is detected, the le...

Let I = [0, N − 1] denote the set of indices. We define the set of states S to contain all maps of type I → R for fixed positive N ∈ N (representing the number of agents). For each s ∈ S, i ∈ I, s(i) represents the value held by the agent with ID i. We denote the arbitrarily fixed start state s0. We introduce the function g whose domain MR is the set of non-empty finite multisets of real number...

A two stage approach to co-ordination in a multi-agent society is presented. The first stage involves agents learning to co-ordinate their activities based on local and global utility – the latter being assigned by an Environment Service Node. Each agent aims to maximise its local utility over a single-step or finite horizon, subject to reinforcements being received from the ESN. An agent may r...

This paper presents a multi-agent model to support decisionmaking in organizations. The model is characterized by being interactive, distributed, and incremental and by the use of cognitive maps to represent the knowledge of decision-making actors. The main proposition is to consider the context of concepts belonging to cognitive maps in a way that it represents agent’s mental states, allowing ...

For an agent to engage in substantive dialogues with other agents, there are several complexities which go beyond the scope of standard models of rational agency. In particular, an agent must reason about social attitudes that span more than one agent, as well as the dynamic and fallible process of plan execution. In this paper we sketch a theory of plan execution which allows the representatio...