| Date | Monday, 17th of September, 2018 |
| Place | Building 14, room 505, Waseda University, Tokyo, Japan |
This workshop will be held during ICDL-EpiRob 2018
Please note the room was changed to building 14, room 505
1 Chome-6 Nishiwaseda, Shinjuku-ku, Tōkyō-to 169-0051 https://goo.gl/maps/2W4Qr1s3j4n
As the algorithms for learning single tasks in restricted environments are improving, new challenges have gained relevance. They include multi-task learning, multimodal sensorimotor learning and lifelong adaptation to injury, growth and ageing.
In this workshop we will discuss the developmental processes involved in the emergence of representations of action and perception in humans and artificial agents in continual learning. These processes include action-perception cycle, active perception, continual sensory-motor learning, environmental-driven scaffolding, and intrinsic motivation.
The discussion will be strongly motivated by behavioural and neural data. We hope to provide a discussion friendly environment to connect with research with similar interest regardless of their area of expertise which could include robotics, computer science, psychology, neuroscience, etc. We would also like to devise a roadmap or strategies to develop mathematical and computational models to improve robot performance and/or to attempt to unveil the underlying mechanisms that lead to continual adaptation to changing environment or embodiment and continual learning in open-ended environments.
The primary list of topics covers the following (but not limited to):
Emergence of representations via continual interaction
Continual sensory-motor learning
Action-perception cycle
Active perception
Environmental-driven scaffolding
Intrinsic motivation
Neural substrates, neural circuits and neural plasticity
Human and animal behaviour experiments and models
Reinforcement learning and deep reinforcement learning for life-long learning
Multisensory robot learning
Multimodal sensorimotor learning
Affordance learning
Prediction learning
 | Jochen Triesch Frankfurt Institute of Advanced Studies, Germany Title: Active Efficient Coding |
 | David Ha Google Brain Title: Generative World Models |
 | Kathryn Kasmarik |
| 09:50 – 10:10 | Welcome and introduction |
| 10:10 – 10:50 | Invited talk: David Ha Title: Generative World Models |
| 10:50 – 11:10 | Coffee break |
| Inference and Representations | |
| 11:10 – 11:30 | Where do I move my sensors? Emergence of an internal representation from the sensorimotor flow Valentin Marcel, Sylvain Argentieri and Bruno Gas |
| 11:30 – 11:50 | Active inference in continual learning Pablo Lanillos and Gordon Cheng |
| Sensorimotor Learning | |
| 11:50 – 12:10 | Towards Biological Plausibility of Sensorimotor Learning Models: A Short Review Silvia Pagliarini, Arthur Leblois, and Xavier Hinaut |
| 12:10 – 12:30 | A Computational Model For Action Prediction Development Serkan Bugur, Yukie Nagai, Erhan Oztop, and Emre Ugur |
| Application/Tools | |
| 12:30 – 12:50 | Flatland: A Lightweight First-Person 2-D Environment for Reinforcement Learning Hugo Caselles-Dupré, Louis Annabi, Oksana Hagen, Michael Garcia-Ortiz, and David Filliat |
| 12:50 – 14:10 | Lunch break |
| 14:10 – 14:50 | Invited talk. Jochen Triesch Title: Active Efficient Coding |
| Intrinsic Motivation and alike | |
| 14:50 – 15:10 | Learning Sequences of Policies by using an Intrinsically Motivated Learner and a Task Hierarchy Nicolas Duminy, Alexandre Manoury, Sao Mai Nguyen, Cédric Buche, and Dominique Duhaut |
| 15:10 – 15:30 | Emergent Emotion as a Regulatory Mechanism for a Cognitive Task Implemented on the iCub Robot Murat Kirtay, Lorenzo Vannucci, Egidio Falotico, Cecilia Laschi, and Erhan Oztop |
| Application/Tools | |
| 15:30 – 15:50 | Towards Life Long Learning: Multimodal Learning of MNIST Handwritten Digits Eli Sheppard, Hagen Lehmann, G. Rajendran, Peter E. McKenna, Oliver Lemon, and Katrin S. Lohan |
| 15:50 – 16:10 | Coffee break |
| 16:10 – 16:40 | Invited talk: Kathryn Kasmarik Title: Computational Motivation for Learning, Optimisation and Decision Making |
| 16:40 – 17:40 | Discussion |
| 17:40 – 18:00 | Conclusions and farewell |
Prospective participants in the workshop are required to submit a contribution as:
Submissions must be in PDF following the standard IEEE conference style. Send your PDF manuscript indicating [ICDL-EPIROB 2018] in the subject to:
Selected contributions will be presented during the workshop as spotlight talks and in a poster session.
Contributors to the workshop will be encouraged to submit extended versions of the manuscripts to a special issue on the same name at IEEE Transactions on Cognitive and Developmental Systems (TCDS). Submissions will be peer reviewed consistent with the journal practices. For more information on the Special Issue, click here.
Paper submission deadline: 5th August 2018
Notification of acceptance: 27th August 2018
Camera-ready version: 9th September 2018
Full-day workshop: 17th September 2018
For information about registration for this workshop please refer to the ICDL-EPIROB website. Note that there is the option of “workshop only registration”.
Nicolás Navarro-Guerrero, Aarhus University, Aarhus, Denmark
Sao Mai Nguyen, IMT Atlantique, France
Erhan Öztop, Özyeğin University, Turkey
Junpei Zhong, National Institute of Advanced Industrial Science and Technology (AIST), Japan
