A probabilistic argumentation framework for reinforcement learning agents : towards a mentalistic approach to agent profiles
License
Access Rights
Cadmus Permanent Link
Full-text via DOI
ISBN
ISSN
1387-2532; 1573-7454
Issue Date
Type of Publication
LC Subject Heading
Other Topic(s)
EUI Research Cluster(s)
Initial version
Published version
Succeeding version
Preceding version
Published version part
Earlier different version
Initial format
Citation
Autonomous agents and multi-agent systems, 2019, Vol. 33, No. 1-2, pp. 216-274
Cite
RIVERET, Régis, GAO, Yang, GOVERNATORI, Guido, ROTOLO, Antonino, PITT, Jeremy, SARTOR, Giovanni, A probabilistic argumentation framework for reinforcement learning agents : towards a mentalistic approach to agent profiles, Autonomous agents and multi-agent systems, 2019, Vol. 33, No. 1-2, pp. 216-274 - https://hdl.handle.net/1814/66098
Abstract
A bounded-reasoning agent may face two dimensions of uncertainty: firstly, the uncertainty arising from partial information and conflicting reasons, and secondly, the uncertainty arising from the stochastic nature of its actions and the environment. This paper attempts to address both dimensions within a single unified framework, by bringing together probabilistic argumentation and reinforcement learning. We show how a probabilistic rule-based argumentation framework can capture Markov decision processes and reinforcement learning agents
and how the framework allows us to characterise agents and their argument-based motivations from both a logic-based perspective and a probabilistic perspective. We advocate and illustrate the use of our approach to capture models of agency and norms, and argue that, in addition to providing a novel method for investigating agent types, the unified framework offers a sound basis for taking a mentalistic approach to agent profiles.
and how the framework allows us to characterise agents and their argument-based motivations from both a logic-based perspective and a probabilistic perspective. We advocate and illustrate the use of our approach to capture models of agency and norms, and argue that, in addition to providing a novel method for investigating agent types, the unified framework offers a sound basis for taking a mentalistic approach to agent profiles.
Table of Contents
Additional Information
Published March 2019
External Links
Publisher
Geographical Coverage
Temporal Coverage
Version
Source
Source Link
Research Projects
Sponsorship and Funder Information
Marie Curie Intra-European Fellowship European Union (EU) [PIEFGA-2012-331472]