1,721,239 research outputs found
Formal methods for responsibility reasoning in multiagent systems
No full textSafe and reliable deployment of collaborative AI-human multiagent systems requires formal semantics and verifiable tools to reason about forward-lookingresponsibilities of agents (e.g., who can/should ensure some properties in prospect) aswell as their backward-looking responsibilities (e.g., who to blame, praise, or see accountable for an already materialized outcome in retrospect) [3, 2, 1]. Modeling andreasoning about responsibility calls for capturing its strategic, epistemic, and normativeaspects for which the community of formal methods possesses apt semantic systemsand reasoning tools. In this talk, we report on a line of research on the application offormal methods and modal logics for reasoning about different forms of responsibilityin multiagent systems [4, 5, 6]. In addition, we overview recent work on the application of responsibility reasoning for task coordination, discuss open problems [7], andhighlight the potentials of formal responsibility reasoning in AI systems
Responsibility of AI systems
No full textTo support the trustworthiness of AI systems, it is essential to have precise methods to determine what or who is to account for the behaviour, or the outcome, of AI systems. The assignment of responsibility to an AI system is closely related to the identification of individuals or elements that have caused the outcome of the AI system. In this work, we present an overview of approaches that aim at modelling responsibility of AI systems, discuss their advantages and shortcomings to deal with various aspects of the notion of responsibility, and present research gaps and ways forward
Quantified degrees of group responsibility: extended abstract
No full textThis paper builds on an existing notion of group responsibility and proposes two ways to define the degree of group responsibility: structural and functional degrees of responsibility. These notions measure the potential responsibilities of (agent) groups for avoiding a state of affairs. According to these notions, a degree of responsibility for a state of affairs can be assigned to a group of agents if, and to the extent that, the group has the potential to preclude the state of affairs
Dynamics of Causal Dependencies in Multi-agent Settings.
No full textIn this paper we discuss how causal models can be used for modeling multi-agent interaction in complex organizational settings, where agents’ decisions may depend on other agents’ decisions as well as the environment. We demonstrate how to reason about the dynamics of such models using concurrent game structures where agents can change the organisational setting and thereby their decision dependencies. In such concurrent game structure, agents can choose to modify their reactions on other agents’ decisions and on the environment by intervening on their part of a causal model. We propose a generalized notion of interventions in causal models that allow us to model and reason about the dynamics of agents’ dependencies in a multi-agent system. Finally, we discuss how to model uncertainty and reason about agents’ responsibility concerning their dependencies and thereby their choices.</p
Combined Proceedings of the Second International Workshop on Coordination and Organization (CoOrg 2006) and the Second International Workshop on Methods and Tools for Coordinating Concurrent, Distributed and Mobile Systems (MTCoord 2006)
No full textMonitoring norms: a multi-disciplinary perspective
Full text linkThe concept of a norm is found widely across fields including artificial intelligence, biology, computer security, cultural studies, economics, law, organizational behaviour and psychology. The concept is studied with different terminology and perspectives, including individual, social, legal and philosophical. If a norm is an expected behaviour in a social setting, then this article considers how it can be determined whether an individual is adhering to this expected behaviour. We call this process monitoring, and again it is a concept known with different terminology in different fields. Monitoring of norms is foundational for processes of accountability, enforcement, regulation and sanctioning. Starting with a broad focus and narrowing to the multi-agent systems literature, this survey addresses four key questions: what is monitoring, what is monitored, who does the monitoring and how the monitoring is accomplished.Algorithmic
Quantified group responsibility in multi-agent systems
Full text linkThis paper1 builds on an existing notion of group responsibility and proposes two ways to define the degree of group responsibility: structural and functional degrees of responsibility. These notions measure potential responsibilities of agent groups for avoiding a state of affairs. According to these notions, a degree of responsibility for a state of affairs can be assigned to a group of agents if, and to the extent that, the group of the agents have potential to preclude the state of affairs. These notions will be formally specified and their properties will be analyzed.</p
Reasoning About Responsibility in Autonomous Systems: Challenges and Opportunities
No full textEnsuring the trustworthiness of autonomous systems and artificial intelligenceis an important interdisciplinary endeavour. In this position paper, we argue thatthis endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e., situations in which a group is responsible, but individuals’ responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g., for completing a task in future) and who can be seen as responsible retrospectively (e.g., for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of Trustworthy Autonomous Systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road-map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society
- …
