*** Apologies for cross-posting *** Dear colleagues, this mail is to invite you to "IMOL2017 – Third International Workshop on Intrinsically Motivated Open-ended Learning" that will be held in Rome, October 4th-5th-6h, 2017. IMOL 2017 is the third international workshop on Intrinsically Motivated Open-ended Learning. Following previous editions, IMOL 2017 aims to further explore the promise of intrinsically motivated open-ended lifelong learning in robots and artificial systems. *We are opening the call for participation and posters (more details on the website and below) with deadline July 16th, 2017*. More info available at imol-conf.org and below. Best wishes, the organizers: Gianluca Baldassarre, Vieri Giuliano Santucci, Pierre-Yves Oudeyer, Andrew Barto ------------------------------------------------------------ ---------------------------------------- *IMOL2017 – Third International Workshop on Intrinsically Motivated Open-ended Learning* Organizers: Gianluca Baldassarre, Vieri Giuliano Santucci, Pierre-Yves Oudeyer, Andrew Barto We are pleased to announce the “Third International Workshop on Intrinsically-Motivated Open-ended Development (IMOL2017)”, which will be held in Rome, Italy, on 4-5-6 October 2017 in a beautiful central location. <http://www.residenzadiripetta.com/it/> All information regarding the workshop, including an extended description of the its scope, can be found in the website imol-conf.org Following two previous workshops, the highly focused “Third International Workshop on Intrinsically-Motivated Open-ended Development (IMOL2017)” aims to further explore the promise of intrinsically motivated open-ended lifelong learning. The workshop aims to be a highly interactive event. To this purpose, it will feature high profile keynote presentations and the participation of an audience of about 60 people. It will foster close interaction among the participants by enabling intense peer-to-peer discussions, poster sessions, and collective round tables directed toward specific objectives. It will take place at a lovely venue in the center of Rome fostering interactions, with evenings devoted to autonomous exploration of the city. It will be followed by a call for papers to be published in an open journal special issue (e.g. a Frontiers in Neurorobotics Research Topic). *Aims of the Workshop* The Workshop will occur over three whole days, with the last session of each day dedicated to a plenary discussion targeting three important topics: (1) The identification of the most important open challenges in the field of autonomous open-ended lifelong learning, with the aim of compiling a list of high-impact goals identified as important next-steps. (2) The definition of one or more benchmarks for evaluating models and architectures for autonomous open-ended learning (at a later date, an open competition will be held based on the benchmark). (3) The identification of the most promising approaches and techniques to tackle the open challenges identified under point (1). *Topics of interest* - Autonomous robots lifelong learning - Multi-task reinforcement learning - Deep reinforcement learning - Intrinsic motivations - Curriculum learning - Goal self-generation - Multiple task solution and parameterized skills - Neural/probabilistic representations and abstractions Architectures for open-ended learning - Goal-based skill learning - Knowledge transfer and avoidance of catastrophic forgetting - Compositionality and chunking - Hierarchies of goals and skills - Mitigating risks of real-world deployment of open-ended learning systems *Current list of invited speakers* - Baldassarre, Gianluca - Barto, Andrew - Bellemare, Marc - Calinon, Sylvain - Cangelosi, Angelo - Konidaris, George - Merrick, Kathryn - Natale, Lorenzo - O’Regan, Kevin - Oudeyer, Pierre-Yves - Peters, Jan - Polani, Daniel - Reinhart, Felix - Rolf, Matthias - Ruecker, Elmar - Santucci, Vieri Giuliano - Stulp, Freek - Triesch, Jochen - Uchibe, Eiji *Call for Application* Participation in the workshop is free of charge and includes the lunches for the three days. However, the workshop is limited to a restricted number of people given the capacity of the venue and the aim of the event. Prospective attendees should express their interest in participating by submitting the form downloadable from the link below, and their willingness (or not) to contribute a poster. In this case, people is also invited to submit a short/extended abstract (max 2 pages), possibly including figures. The submissions will be selected on the basis of the quality and of how well they fit the workshop’s aims. Both senior and young researchers, including Ph.D. students, are encouraged to submit to ensure a full representation of the community. Moreover, applicants are also requested to indicate in the form their willingness to participate in a special issue in Frontiers in Neurorobotics. This request aims to investigate the overall interest for the initiative, which will be followed by a standard Frontiers call after the workshop. Application deadline: July 16th, 2017 Notification of acceptance: July 27th, 2017 Please submit the form downloadable here <http://www.imol-conf.org/wp-content/uploads/2017/05/IMOL2017_ApplicationForm.pdf> and the optional abstract (subject: “IMOL2017 submission: name, last name”) to: *imol.conf@gmail.com <imol.conf@gmail.com>* ------------------------------------------------------------ ---------------------------------------- -- .|.CS...|.......|...............|..|......US.|||.|||||.||.||||..|...|....... Gianluca Baldassarre, Ph.D., Laboratory of Computational Embodied Neuroscience, Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale delle Ricerche (LOCEN-ISTC-CNR), Via San Martino della Battaglia 44, I-00185 Roma, Italy E-mail: gianluca.baldassarre@istc.cnr.it Web: http://www.istc.cnr.it/people/gianluca-baldassarre Tel: +39 06 44 595 231 Fax: +39 06 44 595 243 Motto: 'Learn from the past, live in(tensely) the present, dream for the future' Life mission statement: 'Serve humanity through core knowledge' ...CS.|||.||.|||.||..|.......|........|...US.|.|....||..|..|......|.........