Imperial College London
Alternate

ProfessorJeremyPitt

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor of Intelligent and Self-Organising Systems
 
 
 
//

Contact

 

+44 (0)20 7594 6318j.pitt Website

 
 
//

Assistant

 

Ms Joan O'Brien +44 (0)20 7594 6316

 
//

Location

 

1010Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Riveret:2019:10.1007/s10458-019-09404-2,
author = {Riveret, R and Gao, Y and Governatori, G and Rotolo, A and Pitt, J and Sartor, G},
doi = {10.1007/s10458-019-09404-2},
journal = {Autonomous Agents and Multi-Agent Systems},
pages = {216--274},
title = {A probabilistic argumentation framework for reinforcement learning agents: towards a mentalistic approach to agent profiles},
url = {http://dx.doi.org/10.1007/s10458-019-09404-2},
volume = {33},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.
AU  - Riveret,R
AU  - Gao,Y
AU  - Governatori,G
AU  - Rotolo,A
AU  - Pitt,J
AU  - Sartor,G
DO  - 10.1007/s10458-019-09404-2
EP  - 274
PY  - 2019///
SN  - 1387-2532
SP  - 216
TI  - A probabilistic argumentation framework for reinforcement learning agents: towards a mentalistic approach to agent profiles
T2  - Autonomous Agents and Multi-Agent Systems
UR  - http://dx.doi.org/10.1007/s10458-019-09404-2
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000461140300007&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://link.springer.com/article/10.1007%2Fs10458-019-09404-2
VL  - 33
ER  -
Download