6 January 2024 in Autonomous Agents and Multi-Agent Systems
Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the field of multi-agent deep reinforcement learning (MADRL), agents can improve the overall learning performance and achieve their objectives by communication. Agents can communicate various types of messages, either to all agents or to specific agent groups, or conditioned on specific constraints. With the growing body of research work in MADRL with communication (Comm-MADRL), there is a lack of a systematic and structural approach to distinguish and classify existing Comm-MADRL approaches. In this paper, we survey recent works in the Comm-MADRL field and consider various aspects of communication that can play a role in designing and developing multi-agent reinforcement learning systems. With these aspects in mind, we propose 9 dimensions along which Comm-MADRL approaches can be analyzed, developed, and compared. By projecting existing works into the multi-dimensional space, we discover interesting trends. We also propose some novel directions for designing future Comm-MADRL systems through exploring possible combinations of the dimensions.
5 June 2022 in AI & SOCIETY
To 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.
16 March 2024 in Autonomous Agents and Multi-Agent Systems
Guideline of Comm-MADRL systems. The guideline positions dimensions where communication influences interaction with the environment and training phases.
27 November 2015 in Autonomous Agents and Multi-Agent Systems
In an organisational setting such as an online marketplace, an entity called the ‘organisation’ or ‘institution’ defines interaction protocols, monitors agent interaction, and intervenes to enforce the interaction protocols. The organisation might be a software system that thus regulates the marketplace, for example. In this article we abstract over application-specific protocols and consider commitment lifecycles as generic interaction protocols. We model interaction protocols by explicitly-represented norms, such that we can operationalise the enforcement of protocols by means of norm enforcement, and we can analyse the protocols by a logical analysis of the norms. We adopt insights and methods from commitment-based approaches to agent interaction as well as from norm-based approaches to agent behaviour governance. First, we show how to use explicitly-represented norms to model commitment dynamics (lifecycles). Second, we introduce an operational semantics to operationalise norm enforcement. Third, we show how to logically analyse interaction protocols by means of commitment dynamics and norm enforcement. The model, semantics, and analysis are illustrated by a running example from a vehicle insurance domain.
16 June 2020 in Autonomous Agents and Multi-Agent Systems
To achieve system-level properties of a multiagent system, the behavior of individual agents should be controlled and coordinated. One way to control agents without limiting their autonomy is to enforce norms by means of sanctions. The dynamicity and unpredictability of the agents’ interactions in uncertain environments, however, make it hard for designers to specify norms that will guarantee the achievement of the system-level objectives in every operating context. In this paper, we propose a runtime mechanism for the automated revision of norms by altering their sanctions. We use a Bayesian Network to learn, from system execution data, the relationship between the obedience/violation of the norms and the achievement of the system-level objectives. By combining the knowledge acquired at runtime with an estimation of the preferences of rational agents, we devise heuristic strategies that automatically revise the sanctions of the enforced norms. We evaluate our heuristics using a traffic simulator and we show that our mechanism is able to quickly identify optimal revisions of the initially enforced norms.