Applications are invited for a Postdoc at SequeL, Inria Lille.
Keywords: reinforcement learning, multi-armed bandit, transfer learning, exploration-exploitation, non-stationary environments representation learning, hierarchical learning. Research Topic: Multi-armed bandit and reinforcement learning The main objective of this postdoc position is to advance the state-of-the-art in the field of multi-armed bandit and reinforcement learning (RL) in general, with a particular focus on the development of novel transfer learning algorithms. Reinforcement learning (RL) formalizes the problem of learning an optimal behavior policy from the experience directly collected from an unknown environment. Such general model already provides powerful tools that can be used to learn from data in a very diverse range of applications (e.g., see successful applications of RL to computer games, energy management, logistics, and autonomous robotics). Nonetheless, practical limitations of current algorithms encouraged research in developing efficient ways to integrate expert prior knowledge into the learning process. Although this improves the performance of RL algorithms, it dramatically reduces their autonomy, since it requires a constant supervision by a domain expert. A solution to this problem is provided by transfer learning , i.e., extract knowledge from direct experience and transfer it through different tasks to improve the learning process . The research is postdoc’s research activity will focus on (but not limited to) three main elements of transfer in RL: exploration-exploitation strategies in changing environments, transfer of general representation, hierarchical learning. The research will be primarily theoretical and algorithmic in the attempt of defining new rigorous and principled solutions to transfer in RL and/or improve existing solutions in multi-armed bandit and RL. Profile By the time of the beginning of the postdoc, the applicant should have a Ph.D. in Computer Science, Statistics, or related fields with background in reinforcement learning, bandits, or optimization. Preference will go to candidates with strong mathematical background and good publication record. The working language in the lab is English. How to apply The application should include a brief description of research interests and past experience, a CV, degrees and grades, a copy of the PhD thesis (or a draft thereof), motivation letter (short but pertinent to this call), relevant publications, and other relevant documents. Candidates should provide letter(s) of recommendation and contact information to reference persons. Please send your application in one single pdf to alessandro.lazaric-at-inria.fr . The deadline for the application is March 15 , 2016. The final decision will be communicated at the beginning of April. * Application closing date: March 15 , 2016 * Interviews: shortly after the deadline * Duration: 1 year renewable for 1 year more * Starting date: May 1st, 2016 (flexible) * Contact: Alessandro Lazaric * Place: SequeL, Inria Lille - Nord Europe Working environment The postdoc will work at SequeL ( https://sequel.lille.inria.fr/ ) lab at Inria Lille - Nord Europe located in Lille. Inria ( http://www.inria.fr/ ) is France's leading institution in Computer Science, with over 2800 scientists employed, of which around 250 in Lille. Lille is the capital of the north of France, a metropolis with 1 million inhabitants, with excellent train connection to Brussels (30 min), Paris (1h) and London (1h30). The research team SequeL (Sequential Learning) is composed of about 20 members working in machine learning, notably in reinforcement learning, multi-armed bandit, statistical learning, and sequence prediction. The postdoc grant is co-funded by the ANR ExTra-Learn project, which is entirely focused on the problem of transfer in RL. Benefits * Salary: 2621 € * Salary after taxes : around 2115.29€ * Possibility of French courses * Help for housing * Participation for public transport * Scientific Resident card and help for husband/wife visa
_______________________________________________ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai