A probabilistic argumentation framework for reinforcement learning agents. / Riveret, Régis; Gao, Yang; Governatori, Guido; Rotolo, Antonino; Pitt, Jeremy; Sartor, Giovanni.

In: Autonomous Agents and Multi-Agent Systems, Vol. 33, No. 1-2, 03.2019, p. 216-274.

Research output: Contribution to journalArticle

Published

Standard

A probabilistic argumentation framework for reinforcement learning agents. / Riveret, Régis; Gao, Yang; Governatori, Guido; Rotolo, Antonino; Pitt, Jeremy; Sartor, Giovanni.

In: Autonomous Agents and Multi-Agent Systems, Vol. 33, No. 1-2, 03.2019, p. 216-274.

Research output: Contribution to journalArticle

Harvard

Riveret, R, Gao, Y, Governatori, G, Rotolo, A, Pitt, J & Sartor, G 2019, 'A probabilistic argumentation framework for reinforcement learning agents', Autonomous Agents and Multi-Agent Systems, vol. 33, no. 1-2, pp. 216-274. https://doi.org/10.1007/s10458-019-09404-2

APA

Riveret, R., Gao, Y., Governatori, G., Rotolo, A., Pitt, J., & Sartor, G. (2019). A probabilistic argumentation framework for reinforcement learning agents. Autonomous Agents and Multi-Agent Systems, 33(1-2), 216-274. https://doi.org/10.1007/s10458-019-09404-2

Vancouver

Riveret R, Gao Y, Governatori G, Rotolo A, Pitt J, Sartor G. A probabilistic argumentation framework for reinforcement learning agents. Autonomous Agents and Multi-Agent Systems. 2019 Mar;33(1-2):216-274. https://doi.org/10.1007/s10458-019-09404-2

Author

Riveret, Régis ; Gao, Yang ; Governatori, Guido ; Rotolo, Antonino ; Pitt, Jeremy ; Sartor, Giovanni. / A probabilistic argumentation framework for reinforcement learning agents. In: Autonomous Agents and Multi-Agent Systems. 2019 ; Vol. 33, No. 1-2. pp. 216-274.

BibTeX

@article{d3a53b187bc34c5b91acda519ec0519e,
title = "A probabilistic argumentation framework for reinforcement learning agents",
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.",
author = "R{\'e}gis Riveret and Yang Gao and Guido Governatori and Antonino Rotolo and Jeremy Pitt and Giovanni Sartor",
year = "2019",
month = mar,
doi = "10.1007/s10458-019-09404-2",
language = "English",
volume = "33",
pages = "216--274",
journal = "Autonomous Agents and Multi-Agent Systems",
issn = "1387-2532",
publisher = "Springer",
number = "1-2",

}

RIS

TY - JOUR

T1 - A probabilistic argumentation framework for reinforcement learning agents

AU - Riveret, Régis

AU - Gao, Yang

AU - Governatori, Guido

AU - Rotolo, Antonino

AU - Pitt, Jeremy

AU - Sartor, Giovanni

PY - 2019/3

Y1 - 2019/3

N2 - 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.

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.

U2 - 10.1007/s10458-019-09404-2

DO - 10.1007/s10458-019-09404-2

M3 - Article

VL - 33

SP - 216

EP - 274

JO - Autonomous Agents and Multi-Agent Systems

JF - Autonomous Agents and Multi-Agent Systems

SN - 1387-2532

IS - 1-2

ER -