<html><head><meta http-equiv="Content-Type" content="text/html charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><div><br></div><div><div>[We apologize if you receive multiple copies of this message]</div><div><br></div><div><div><b>Call for postdoc application in Lifelong Deep Learning for Robotics, at Flowers Lab, Inria</b> (Bordeaux, France)</div><div><br></div><div>Deadline: 30th march</div><div>Eligibility: candidates should have obtained their PhD diploma after 1st september 2015</div><div><a href="https://urldefense.proofpoint.com/v2/url?u=https-3A__goo.gl_32SAEw&d=DgMFAg&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=QgI_fDPhVJqEea11agwUmw9MvmMfgsw0G2G1o8g4G2U&s=zPT9zIHVXqjtN4vquh8cdswMecUFp4Sc6uGbzLhz8ko&e=">https://flowers.inria.fr</a></div><div><br></div><div><div>We are searching outstanding candidates for a <b>postdoc </b>(16 months) who will be working on algorithms </div><div>for lifelong Deep Learning for robotics, and in particular:</div><div>- unsupervised or self-supervised deep learning</div><div>- generative networks such as GANs and/or variational auto-encoders</div><div><div>- deep reinforcement learning for robotic control</div><div>- Intrinsic motivation</div><div>- multi-task reinforcement learning, auxiliary tasks</div></div><div><br></div><div>Selected candidates will have the opportunity to work with one of the robotics platforms of the Flowers lab, including</div><div>several Poppy Humanoid robots and starting from the experimental setup that was runner up for the NIPS 2016 demonstration award, </div><div>and showing intrinsically motivated multi-task reinforcement learning in real-time on real robots, with interaction with humans </div><div>(<a href="http://goo.gl/03FW4k">http://goo.gl/03FW4k</a>), or the Baxter humanoid robot (<a href="http://goo.gl/nSS7Yp">http://goo.gl/nSS7Yp</a>).</div><div><br></div><div>Candidates should already have shown very strong experience and achievements, shown by publications in top-tier AI/machine learning</div><div>conferences and journals (e.g. NIPS, ICML, ICLR) in either:</div><div>- deep learning (both theory and practical implementations)</div><div>- Reinforcement learning for policy learning of parameterized skills in robotics</div><div><br></div><div><div><div><div><b>How to apply</b></div><div>===========</div><div><br></div><div>CVs and letters of motivation should be sent to Pierre-Yves Oudeyer (<a href="mailto:pierre-yves.oudeyer@inria.fr">pierre-yves.oudeyer@inria.fr</a>) before 30th march.</div><div>The successful candidate would begin to work in september 2017.</div></div><div><div>Deadline: 30th march</div><div>Eligibility: candidates should have obtained their PhD diploma after 1st september 2015</div><div></div></div><div><br></div><div><div>Pierre-Yves Oudeyer </div><div>Research director, Inria</div><div>Head of Flowers Lab</div><div>Inria and Ensta ParisTech</div><div><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__goo.gl_HGwDC2&d=DgMFAg&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=QgI_fDPhVJqEea11agwUmw9MvmMfgsw0G2G1o8g4G2U&s=gmQ2k5uaQIkmCh8F9D8kVSpmZ7a2L0n_aMHL8KEIzyg&e=">http://www.pyoudeyer.com</a></div></div></div><div><a href="https://flowers.inria.fr/">https://flowers.inria.fr</a></div></div><div><br></div><div>More info:</div><div><br></div><div><b>The Flowers Lab: developmental robotics and lifelong multitask machine learning</b></div><div>===================================================================</div><div><br></div><div>The Flowers Lab, headed by Pierre-Yves Oudeyer, gathers a team of ~20 members and has been one of the pioneers of developmental robotics and lifelong machine learning</div><div>and artificial intelligence in the last decade, in particular through developping models of <b>intrinsically motivated learning of repertoires </b><b>of skills</b> that have both contributed </div><div>to advance understanding of <b>human curiosity and development</b>, and to advance incremental online multitask <b>machine learning techniques in difficult high-dimensional </b></div><div><b>robotic spaces</b>. </div><div><br></div><div>This work in the Flowers lab is conducted in the context of large international projects (e.g. ERC grant, European projects 3rdHand and DREAM, HFSP project Neurocuriosity),</div><div>with <b>interdisicplinary collaborations with other labs in neuroscience, psychology, machine learning and robotics</b>. The successful candidates would be directly</div><div>involved in these international collaborations. </div><div><br></div><div>The Flowers lab has recently spin-off the Pollen Robotics startup company, and is involved in multiple collaborations with industrials through Inria's strong</div><div>support towards impacting both science and industry. </div><div><br></div><div><b>Inria and EnstaParistech</b></div><div>===================</div><div><br></div><div>The lab is within Inria, which is a prestigious, and also the largest, public European research insitution focused on computer science, mathematics and their applications.</div><div>Inria's teams and researchers (> 2800 employees) have received prestigious awards, coordinate many international projects, and have created strong innovations now used in many</div><div>parts of industry. Inria research center in Bordeaux gathers around 300 researchers. </div><div>The Flowers Lab is also associated to EnstaParisTech, which is a prestigious French engineering school (university).</div><div><br></div><div><b>Bordeaux </b></div><div>========</div><div><br></div><div>The Flowers lab in Bordeaux is located in a great building on the border of one of the world most famous vineyard, and 10mn by tram from Bordeaux town center</div><div>(and 2 hours from Paris through high-speed trains): <a href="https://urldefense.proofpoint.com/v2/url?u=https-3A__www.inria.fr_en_centre_bordeaux&d=DgMFAg&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=QgI_fDPhVJqEea11agwUmw9MvmMfgsw0G2G1o8g4G2U&s=h3UuNID7EocJsv9cgJI3xbGj1OBGijUG-8Xwikt9MnY&e=">https://www.inria.fr/en/centre/bordeaux</a></div><div>Bordeaux has been recently rated by Lonely Planet as the world's best city to visit: <a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__www.independent.co.uk_travel_news-2Dand-2Dadvice_best-2Dcities-2Din-2Dthe-2Dworld-2Dtop-2D10-2Dlonely-2Dplanet-2Dbordeaux-2Dcape-2Dtown-2Dla-2Da7379066.html&d=DgMFAg&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=QgI_fDPhVJqEea11agwUmw9MvmMfgsw0G2G1o8g4G2U&s=V_OI8STEAyhH9Zs1Aawi7zUuplWEEJMtFPqA8utA6Gk&e=">http://www.independent.co.uk/travel/news-and-advice/best-cities-in-the-world-top-10-lonely-planet-bordeaux-cape-town-la-a7379066.html</a></div><div><br></div></div></div></div></body></html>