<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"><!-- P {margin-top:0;margin-bottom:0;} --></style>
</head>
<body dir="ltr">
<div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Helvetica,sans-serif;" dir="ltr">
<p></p>
<div style="font-family: Calibri, Helvetica, sans-serif, EmojiFont, "Apple Color Emoji", "Segoe UI Emoji", NotoColorEmoji, "Segoe UI Symbol", "Android Emoji", EmojiSymbols; font-size: 16px; margin-top: 0px; margin-bottom: 0px;">
<font size="3"><span style="font-size: 12pt;">Deadline Extended! - The Chef's Hat Cup @ IJCAI2021</span></font><br>
</div>
<div style="font-family: Calibri, Helvetica, sans-serif, EmojiFont, "Apple Color Emoji", "Segoe UI Emoji", NotoColorEmoji, "Segoe UI Symbol", "Android Emoji", EmojiSymbols; font-size: 16px;">
<font color="black">
<div>
<div id="divtagdefaultwrapper"><font face="Calibri,Helvetica,sans-serif,EmojiFont,Apple Color Emoji,Segoe UI Emoji,NotoColorEmoji,Segoe UI Symbol,Android Emoji,EmojiSymbols" size="3" color="black"><span id="divtagdefaultwrapper" style="font-size: 12pt;">
<div><br>
</div>
<div><br>
</div>
<div>I. Aim and Scope</div>
<div><br>
</div>
<div>Most of the current Reinforcement-Learning solutions, although having real-world-inspired scenarios, focus on a direct space-action-reward mapping between the agent's actions and the environment’s state. That translates to agents that can adapt to dynamic
scenarios, but, when applied to competitive and/or cooperative cases, fail to assess and deal with the impact of their opponents. In most cases, when these agents choose an action, they do not take into consideration how other agents can affect the state of
the scenario. In competitive scenarios, the agents have to learn decisions that a) maximize their chances of winning the game, and b) minimize their adversaries' goals, while in cooperative scenarios b) is inverted. Besides dealing with complex scenarios,
such solutions would have to deal with the dynamics between the agents themselves. In this regard, social reinforcement learning is still behind the mainstream applications and demonstrations of the last years.</div>
<div><br>
</div>
<div>We introduce here the Chef's Hat Cup, a competition that aims at the development of the most challenging artificial players!</div>
<div><br>
</div>
<div>The competition is separated into two tracks: a competitive and a cooperative scenario. In the first track, the participants will use the already available simulation environment to develop the most effective agents to play the Chef’s Hat card game and
be the winner. In the second track, they will have to develop an agent that can increase the chances of a dummy agent winning the game.</div>
<div><br>
</div>
<div>More information: https://www.whisperproject.eu/chefshat#competition</div>
<div><br>
</div>
<div>II. Deadlines</div>
<div><br>
</div>
<div>Starting Date: April 20, 2021</div>
<div><br>
</div>
<div>Final submission: July 15, 2021</div>
<div><br>
</div>
<div>Winners Announcement: July 29, 2021</div>
<div><br>
</div>
<div><br>
</div>
<div>III. Team Registration</div>
<div><br>
</div>
<div>Teams of up to five persons are invited to participate in the competition.</div>
<div><br>
</div>
<div>You can register by sending the following information:</div>
<div><br>
</div>
<div>Team name</div>
<div>Participant Names and affiliation</div>
<div><br>
</div>
<div>to this email: pablo.alvesdebarros@iit.it</div>
<div><br>
</div>
<div>IV. Prizes</div>
<div><br>
</div>
<div>
<div>The prizes will be sponsored by the Contact Unit at the Italian Institute of Technology, and will be organized as follows:</div>
<div><br>
</div>
<div>Competitive Track</div>
<div> - Winner – 300 EUR</div>
<div> - Second – 150 EUR</div>
<div> - Third – 50 EUR</div>
<div><br>
</div>
<div>Cooperative Track</div>
<div> - Winner – 300 EUR</div>
<div> - Second – 150 EUR</div>
<div> - Third – 50 EUR</div>
</div>
<div><br>
</div>
<div>V. Organizers</div>
<div><br>
</div>
<div>Pablo Barros, Italian Institute of Technology (IIT), Italy</div>
<div>Leandro Honorato, University of Pernambuco, Brazil</div>
<div>Marco Matarese, Italian Institute of Technology (IIT), Italy</div>
<div>Alessandra Sciutti, Italian Institute of Technology (IIT), Italy</div>
</span></font></div>
</div>
</font></div>
<br>
<p></p>
<p><br>
</p>
<div id="Signature">
<div id="divtagdefaultwrapper" dir="ltr" style="font-size: 12pt; color: rgb(0, 0, 0); font-family: Calibri, Helvetica, sans-serif, EmojiFont, "Apple Color Emoji", "Segoe UI Emoji", NotoColorEmoji, "Segoe UI Symbol", "Android Emoji", EmojiSymbols;">
<p></p>
<p class="x_MsoNormal"><span style="font-size:9pt">----------------------------------------</span></p>
<p></p>
<span style="font-size:9pt">Dr. Pablo Barros</span><br>
<span style="font-size:9pt">Postdoctoral Researcher - </span><span style="font-size:9pt">CONTACT Unit</span><br>
<span style="font-size:9pt">Istituto Italiano di Tecnologia – Center for Human Technologies
</span><br>
<span style="font-size:9pt">Via Enrico Melen 83, Building B 16152 Genova, Italy</span><br>
<span lang="EN-US" style="font-family:"Calibri",sans-serif,serif,"EmojiFont"; font-size:9pt">email:
</span><span lang="EN-US" style="color:rgb(0,0,0); font-family:"Calibri",sans-serif,serif,"EmojiFont"; font-size:9pt">pablo.alvesdebarros@iit.it</span><span style="font-size:9pt">
</span><span lang="EN-US" style="font-family:"Calibri",sans-serif,serif,"EmojiFont""></span><br>
<span lang="EN-US" style="font-family:"Calibri",sans-serif,serif,"EmojiFont"; font-size:9pt">website:
</span><span lang="EN-US" style="color:rgb(5,99,193); font-family:"Calibri",sans-serif,serif,"EmojiFont""><a href="http://www.pablobarros.net" class="OWAAutoLink" id="LPNoLP"><span style="font-size:9pt">https://www.pablobarros.net</span></a></span><a href="https://www.p" target="_blank" rel="noopener noreferrer" id="LPNoLP"><span lang="EN-US" style="color:rgb(5,99,193); font-family:"Calibri",sans-serif,serif,"EmojiFont""></span></a><span lang="EN-US" style="font-family:"Calibri",sans-serif,serif,"EmojiFont""></span><br>
<span style="font-size:9pt">twitter: @</span><span style="font-size:9pt">PBarros_br</span>
<p><br>
</p>
</div>
</div>
</div>
</body>
</html>