The cognitive agent model presented in this paper generates  prior and retrospective ownership states for an action based on principles from recent neuro-logical theories. A prior ownership state is affected by prediction of the effects of a prepared action, and exerts control by strengthening or suppressing actual execution of the action. A retrospective ownership state depends on whether the sensed consequences co-occur with the predicted consequences, and is the basis for acknowledging authorship of actions, for example, in social context. It is shown how poor action effect prediction capabilities can lead to reduced retrospective ownership states, as in persons suffering from schizophrenia.

The design of multiagent simulations devoted to complex systems, addresses the issue of modeling behaviors that are involved at different space, time, behavior scales, each one being relevant so as to represent a feature of the phenomenon. We propose here a generic formalism intended to represent multiple environments, endowed with their own spatiotemporal scales and with behavioral rules for the agents they contain. An environment can be nested inside any agent, which itself is situated in one or more environments. This leads to a lattice decomposition of the global system, which appears to be necessary for an accurate design of multi-scale systems. This uniform representation of entities and behaviors at each abstraction level relies upon an interaction-oriented approach for the design of agent simulations, which clearly separates agents from interactions, from the modeling to the code. We also explain the implementation of our formalism within an existing interaction-based platform.

We address the issue, in cognitive agents, of possible loss of previous information, which later might turn out to be correct when new information becomes available. To this aim, we propose a framework for changing the agent's mind without erasing forever previous information, thus allowing its recovery in case the change turns out to be wrong. In this new framework, a piece of information is represented as an argument which can be more or less accepted depending on the trustworthiness of the agent who proposes it. We adopt possibility theory to represent uncertainty about the information, and to model the fact that information sources can be only partially trusted. The originality of the proposed framework lies in the following two points: (i) argument reinstatement is mirrored in belief reinstatement in order to avoid the loss of previous information; (ii) new incoming information is represented under the form of arguments and it is associated with a plausibility degree depending on the trustworthiness of the information source.

The Game Description Language is a high-level, rule-based formalisms for communicating the rules of arbitrary  games to general game-playing systems, whose challenging task is to learn to play previously unknown games without human intervention. Originally designed for deterministic games with complete information about the game state, the language was recently extended to include randomness and imperfect information. However, determining the extent to which this enhancement allows to describe truly arbitrary games was left as an open problem. We provide a positive answer to this question by relating the extended Game Description Language to the universal, mathematical concept of extensive-form games, proving that indeed just any such game can be described faithfully.

Monitoring team activity is beneficial when human teams cooperate in the enactment of a joint plan. Monitoring allows teams to maintain awareness of each other's progress within the plan and it enables anticipation of information needs. Humans find this difficult, particularly in time-stressed and uncertain environments. In this paper we introduce a probabilistic model, based on Conditional Random Fields, to automatically recognise the composition of teams and the team activities in relation to a plan. The team composition and activities are recognised incrementally by interpreting a stream of spatio-temporal observations.

Unfortunately, this example is a useful analogy can be treated within a unified framework along for many situations in real life, where (individually) rational with seemingly unrelated problems in the fields of judgment behavior leads to a disaster for the society.

We present the notion of Social Instruments as mechanisms that facilitate the emergence of conventions from repeated interactions between members of a society. Specifically, we focus on two social instruments: rewiring and observation. Our main goal is to provide agents with tools that allow them to leverage their social network of interactions when effectively addressing coordination and learning problems, paying special attention to dissolving meta-stable subconventions. Initial experiments throw some light on how Self-Reinforcing Substructures (SRS) in the network prevent full convergence, resulting in reduced convergence rates. The use of an effective composed social instrument (observation + rewiring) allow agents to eliminate the subconventions that otherwise remained meta-stable.

In real-world applications, the effective integration of learning and reasoning in a cognitive agent model is a difficult task. However, such integration may lead to a better understanding, use and construction of more realistic models. Unfortunately, existing models are either oversimplified or require much processing time, which is unsuitable for online learning and reasoning. Currently, controlled environments like training simulators do not effectively integrate learning and reasoning. In particular, higher-order concepts and cognitive abilities have many unknown temporal relations with the data, making it impossible to represent such relationships by hand. We introduce a novel cognitive agent model and architecture for online learning and reasoning that seeks to effectively represent, learn and reason in complex training environments. The agent architecture of the model combines neural learning with symbolic knowledge representation. It is capable of learning new hypotheses from observed data, and infer new beliefs based on these hypotheses. Furthermore, it deals with uncertainty and errors in the data using a Bayesian inference model. The validation of the model on real-time simulations and the results presented here indicate the promise of the approach when performing online learning and reasoning in real-world scenarios, with possible applications in a range of areas.

In weighted voting games, each agent has a weight, and a coalition of players is deemed to be winning if its weight meets or exceeds the given quota. An agent's power in such games is usually measured by her Shapley value, which depends both on the agent's weight and the quota. [Zuckerman et. al., 2008] show that one can alter a player's power significantly by modifying the quota, and investigate some of the related algorithmic issues. In this paper, we answer a number of questions that were left open by [Zuckerman et. al., 2008]: we show that, even though deciding whether a quota maximizes or minimizes an agent's Shapley value is coNP-hard, finding a Shapley value-maximizing quota is easy. Minimizing a player's power appears to be more difficult. However, we propose and evaluate a heuristic for this problem, which takes into account the voter's rank and the overall weight distribution. We also explore a number of other algorithmic issues related to quota manipulation.

Typical solutions for agents assessing trust relies on the circulation of information on the individual level, i.e. reputational images, subjective experi- ences, statistical analysis, etc. This work presents an alternative approach, inspired to the cognitive heuristics enabling humans to reason at a categorial level. The approach is envisaged as a crucial ability for agents in order to: (1) estimate trustworthiness of unknown trustees based on an ascribed mem- bership to categories; (2) learn a series of emer- gent relations between trustees observable proper- ties and their effective abilities to fulfill tasks in sit- uated conditions. On such a basis, categorization is provided to recognize signs (Manifesta) through which hidden capabilities (Kripta) can be inferred. Learning is provided to refine reasoning attitudes needed to ascribe tasks to categories. A series of ar- chitectures combining categorization abilities, indi- vidual experiences and context awareness are eval- uated and compared in simulated experiments.