<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
This post of Research Assistant/Associate (post-doctoral) is to
conduct research on <em>safe reinforcement learning through formal
methods</em><em>, </em>under the direction of Dr Francesco
Belardinelli, within the EPSRC New Investigator Award <em>An
Abstraction-based Technique for Safe Reinforcement Learning</em>.
<p>Autonomous agents learning to act in unknown environments have
been attracting research interest due to their wider implications
for AI, as well as for their applications in key domains,
including robotics, network optimisation, resource allocation.
Currently, one of the most successful approaches is reinforcement
learning (RL). However, to learn how to act, agents are required
to explore the environment, which in safety-critical scenarios
means that they might take dangerous actions, possibly harming
themselves or even putting human lives at risk.</p>
<p>The main goal of this project is to develop Safe through
Abstraction (multi-agent) Reinforcement learning (StAR), a
framework to formally guarantee the safe behaviour of agents
learning to act in unknown environments, through the satisfaction
of safety constraints by the policies synthesized through RL, both
at training and test time. We aim at combining RL and formal
methods to ensure the satisfaction of constraints expressed in
(probabilistic) temporal logic (PTL) in multi-agent environments.</p>
<p>The successful applicant will join the Formal Methods in AI
(FMAI) research group, led by Dr Belardinelli. For further
information on the group and related projects, see: <a
href="https://www.doc.ic.ac.uk/~fbelard/"
class="moz-txt-link-freetext" moz-do-not-send="true">https://www.doc.ic.ac.uk/~fbelard/</a>).</p>
<p>The position offers an exciting opportunity for conducting
internationally leading and impactful research in safe
reinforcement learning. The postholder will be responsible for
researching and delivering abstraction-based methods to guarantee
the safe and trustworthy behaviour of autonomous agents based on
the most widely used RL algorithms. They will also be expected to
submit publications to top-tier conferences and journals in AI.<em></em></p>
<p>To apply, you must have a strong computer science background with
a focus on AI, have experience, including a proven publication
track-record, in at least two of the following areas, as well as
ability and willingness to become familiar with the other: <em>Logic-based
languages and formal methods; Formal verification, including
model checking; (safe) Reinforcement</em>. You should also have:<em></em></p>
<ul>
<li>Research Assistant: A Master’s degree (or equivalent) in
computer science or a related area.</li>
<li>Research Associate: A PhD degree (or equivalent) in computer
science or a related area.</li>
<li>Familiarity with <em>standard reinforcement learning
libraries/data analysis</em>.</li>
<li>Excellent communication skills and ability to work with
others.</li>
<li>Ability to organise your own work and set priorities to meet
deadlines.</li>
</ul>
<p><strong>This position is full-time, fixed term, to start October
2023 for 24 months</strong></p>
<strong>To apply</strong>
<p>Visit <a href="https://www.imperial.ac.uk/jobs/"
class="moz-txt-link-freetext" moz-do-not-send="true">https://www.imperial.ac.uk/jobs/</a>
and search using reference ENG02573. In addition to completing the
online application, candidates should attach:</p>
<ul>
<li>A full CV, with a list of all publications</li>
<li>A 2-page research statement indicating what you see are
interesting research issues relating to the above post and why
your expertise is relevant.</li>
</ul>
<p>Informal enquiries related to the position should be directed to
Dr. Francesco Belardinelli: <a
href="mailto:francesco.belardinelli@imperial.ac.uk"
class="moz-txt-link-freetext" moz-do-not-send="true">francesco.belardinelli@imperial.ac.uk</a>. </p>
<p>For queries regarding the application process contact Jamie
Perrins: <a href="mailto:j.perrins@imperial.ac.uk"
class="moz-txt-link-freetext" moz-do-not-send="true">j.perrins@imperial.ac.uk</a>.</p>
<p><strong>Closing Date: 31 May 2023 (midnight)</strong></p>
</body>
</html>