[PlanetKR] offre postdoc
Andreas HERZIG
andreas.herzig at irit.fr
Thu Mar 24 09:45:18 UTC 2022
Le 23/03/2022 à 16:03, Martin DIEGUEZ LODEIRO a écrit :
> est-ce que tu as les liens de logic @Bonn, folli ... ? Je ne les connais pas.
> Martin.
Voila mes listes: logic at math.uni-bonn.de , folli at folli.info ,
planetkr at kr.org
Tiens, j'en profite pour te faire relire une proposition de postdoc que
je suis en train de rediger. Le truc un peu inhabituel est que je
demande au candidat de rediger une petite proposition ; keske tu en
penses ?
Andi
Postdoc Position on Advanced Planning
=====================================
Deciding and learning how to act pose fundamental problems for an
intelligent agent. AI planning traditionally focusses on the generation
of plans for an individual agent under the hypothesis that no other
agent intervenes and that the planning agent has perfect knowledge of
the environment and the behaviour of actions. More advanced forms of
planning should include things such as reasoning about other agents'
beliefs, goals, intentions and actions; learning from past experiences;
monitoring the actual outcome of actions and learning possibly
unexpected outcomes and dealing with such new outcomes. A further aspect
is that empowering an AI agent with the ability to self-deliberate its
own behavior and act autonomously carries significant risks, which
requires to balance such power with safety: the autonomy of the agent
must be guarded by human-guided specifications and oversight in order to
make it verifiable and comprehensible in human terms and ultimately
trustworthy.
Appliants should propose a short research project related to these
themes, possibly relating it to previous work of ours where we have
contributed to epistemic planning (AIJ) and to planning inspired from
Bratman's theory of intention (KI,JELIA).
The duration of the contract is 18 months (possibly with an extension).
The salary is between 2.263€ and 3.783€ net, depending on the experience
of the candidate. Starting date is June 2022 or later.
* Environment
The Institut de Recherche en Informatique de Toulouse (IRIT) is one of
the biggest computer science labs in France. Its AI Department has a
long-standing tradition of research in knowledge representation and
reasoning. IRIT participates in the ANITI project on hybrid AI.
The postdoc position is within the TAILOR network (Trustworthy AI:
Integrating Learning, Optimization and Reasoning,
https://tailor-network.eu/) in which CNRS-IRIT takes part, and is part
of its workpackage 5 "Deciding and Learning how to Act". TAILOR is one
of four networks of excellence working on aspects of trustworthy AI
funded under the H2020-ICT-48-2020 call.
* Profile and Application
We are looking for a candidate with a background in knowledge
representation and/or machine learning who is interested in their
integration in the context of planning. Candidates should send the
following to Andreas.Herzig at irit.fr before April 15:
• CV;
• Up to 3 reference letters;
• A short proposal of research activities (max 1 page).
* References
• Martin C. Cooper, Andreas Herzig, Faustine Maffre, Frédéric Maris,
Elise Perrotin, Pierre Régnier: A lightweight epistemic logic and its
application to planning. Artif. Intell. 298: 103437 (2021).
• Andreas Herzig, Laurent Perrussel, Zhanhao Xiao, Dongmo Zhang:
Refinement of Intentions. JELIA 2016: 558-563.
• Andreas Herzig, Emiliano Lorini, Laurent Perrussel, Zhanhao Xiao: BDI
Logics for BDI Architectures: Old Problems, New Perspectives. Künstliche
Intell. 31(1): 73-83 (2017).
• Michael Bratman: Intention, Plans, and Practical Reason. Harvard
University Press, Cambridge (1987). Reedited 1999 with CSLI Publications.
• Philip R. Cohen, Hector J. Levesque: Intention is choice with
commitment. J. Artif. Intell. 42(2), 213–261 (1990).
More information about the PlanetKR
mailing list