Please distribute: ------------------------------------------------------------------------ Call for Papers ECML/PKDD 2013 Workshop on Reinforcement Learning with Generalized Feedback: Beyond Numeric Rewards ------------------------------------------------------------------------
<http://www.ke.tu-darmstadt.de/events/PBRL-13/pbrl-13.html> This workshop will be held on Monday, September 23rd 2013, as part of the ECML/PKDD 2013 <http://www.ecmlpkdd2013.org/> conference. BACKGROUND Reinforcement learning is traditionally formalized within the /Markov Decision Process/ (MDP) framework: By taking actions in a stochastic and possibly unknown environment, an agent moves between states in this environment; moreover, after each action, it receives a numeric, possibly delayed reward signal. The agent's learning task then consists of developing a strategy that allows it to act optimally, that is, to devise a policy (mapping states to actions) that maximizes its long-term (cumulative) reward. In recent years, different generalizations of the standard setting of reinforcement learning have emerged; in particular, several attempts have been made to relax the quite restrictive requirement for numeric feedback and to learn from different types of more flexible training information. Examples of generalized settings of that kind include apprenticeship learning, inverse reinforcement learning, multi-objective reinforcement learning, and preference-based reinforcement learning. Learning in these generalized frameworks can be considerably harder than learning in MDPs because rewards cannot be easily aggregated over different states. GOALS AND OBJECTIVES The most important goal of this workshop is to help in unifying and streamlining research on generalizations of standard reinforcement learning, which, for the time being, seem to be pursued in a rather disconnected manner. Indeed, many of the extensions and generalizations discussed above are still lacking a sound theoretical foundation, let alone a generally accepted underlying framework comparable to Markov Decision Processes for conventional reinforcement learning. Besides, many of the commonalities shared by these generalizations have apparently not been recognized or explored so far. A formalization in terms of preferences may provide such a theoretical underpinning. Ideally, the workshop will help the participants to identify some common ground of their work, thereby helping the field move toward a theoretical foundation of reinforcement learning with generalized feedback. Apart from fostering theoretical developments of that kind, we are also interested in identifying and exchanging interesting applications and problems that may serve as benchmarks for qualitative or preference-based reinforcement learning (such as cart-pole balancing or the mountain car for classical reinforcement learning). TOPICS OF INTEREST Topics of interest include but are not limited to * novel frameworks for reinforcement learning beyond MDPs * algorithms for learning from preferences and non-numeric, qualitative, or structured feedback * theoretical results on the learnability of optimal policies, convergence of algorithms in qualitative settings, etc. * applications and benchmark problems for reinforcement learning in non-standard settings. SUBMISSIONS Please e-mail submissions in Springer LNCS format to both workshop chairs. There is no strict page limit, but we encourage authors to stay within the page limits of the main conference (16 pages). We particularly encourage short papers (8 pages or less). Should there be a high turnout in papers with high quality, we will also consider a post-workshop publication, such as a special issue or a book. We like to emphasize, however, that the ambition of the workshop is not to collect mature work ready for publication but to provide a forum of exchange for researchers, with the possibility to discuss ongoing developments and work in progress. IMPORTANT DATES Paper deadline: /June 28, 2013/ Notifications: /July 19, 2013/ Final versions: /August 2, 2013/ Workshop date: /September 23, 2013/ WORKSHOP CHAIRS * Johannes Fürnkranz <mailto:ju...@ke.informatik.tu-darmstadt.de> (TU Darmstadt) * Eyke Hüllermeier <mailto:e...@mathematik.uni-marburg.de> (Universität Marburg) _______________________________________________ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai