The Future of Interactive Machine Learning
Kory Mathewson · Kaushik Subramanian · Mark Ho · Robert Loftin · Joseph L Austerweil · Anna Harutyunyan · Doina Precup · Layla El Asri · Matthew Gombolay · Jerry Zhu · Sonia Chernova · Charles L Isbell · Patrick M Pilarski · Weng-Keen Wong · Manuela Veloso · Julie A Shah · Matthew Taylor · Brenna Argall · Michael Littman

Fri Dec 9th 08:00 AM -- 06:30 PM @ Hilton Diag. Mar, Blrm. A
Event URL: »

Interactive machine learning (IML) explores how intelligent agents solve a task together, often focusing on adaptable collaboration over the course of sequential decision making tasks. Past research in the field of IML has investigated how autonomous agents can learn to solve problems more effectively by making use of interactions with humans. Designing and engineering fully autonomous agents is a difficult and sometimes intractable challenge. As such, there is a compelling need for IML algorithms that enable artificial and human agents to collaborate and solve independent or shared goals. The range of real-world examples of IML spans from web applications such as search engines, recommendation systems and social media personalization, to dialog systems and embodied systems such as industrial robots and household robotic assistants, and to medical robotics (e.g. bionic limbs, assistive devices, and exoskeletons). As intelligent systems become more common in industry and in everyday life, the need for these systems to interact with and learn from the people around them will also increase.

This workshop seeks to brings together experts in the fields of IML, reinforcement learning (RL), human-computer interaction (HCI), robotics, cognitive psychology and the social sciences to share recent advances and explore the future of IML. Some questions of particular interest for this workshop include: How can recent advancements in machine learning allow interactive learning to be deployed in current real world applications? How do we address the challenging problem of seamless communication between autonomous agents and humans? How can we improve the ability to collaborate safely and successfully across a diverse set of users?

We hope that this workshop will produce several outcomes:
- A review of current algorithms and techniques for IML, and a focused perspective on what is lacking;
- A formalization of the main challenges for deploying modern interactive learning algorithms in the real world; and
- A forum for interdisciplinary researchers to discuss open problems and challenges, present new ideas on IML, and plan for future collaborations.

Topics relevant to this workshop include:
Human-robot interaction
Collaborative and/or shared control
Semi-supervised learning with human intervention
Learning from demonstration, interaction and/or observation
Reinforcement learning with human-in-the-loop
Active learning, Preference learning
Transfer learning (human-to-machine, machine-to-machine)
Natural language processing for dialog systems
Computer vision for human interaction with autonomous systems
Transparency and feedback in machine learning
Computational models of human teaching
Intelligent personal assistants and dialog systems
Adaptive user interfaces
Brain-computer interfaces (e.g. human-semi-autonomous system interfaces)
Intelligent medical robots (e.g. smart wheelchairs, prosthetics, exoskeletons)

08:20 AM Opening Remarks, Invited Talk: Michael C. Mozer (Invited Talk) Mike Mozer
09:10 AM A Human-in-the-loop Approach for Troubleshooting Machine Learning Systems, Besmira Nushi, Ece Kamar, Donald Kossmann and Eric Horvitz (Paper Presentation)
09:30 AM Efficient Exploration in Monte Carlo Tree Search using Human Action Abstractions, Kaushik Subramanian, Jonathan Scholz, Charles Isbell and Andrea Thomaz (Paper Presentation)
09:50 AM Invited Talk: Mattew E. Taylor (Invited Talk) Matthew Taylor
10:30 AM Coffee Break 1 (Break)
11:00 AM Invited Talk: Olivier Pietquin (Invited Talk) Olivier Pietquin
11:40 AM Poster Spotlight Talks 1 (Poster Spotlight 1)
12:10 PM Invited Talk: Todd Gureckis (Invited Talk) Todd Gureckis
12:50 PM Lunch Break (Break)
02:00 PM Poster Spotlight Talks 2 (Poster Spotlight 2)
02:30 PM Invited Talk: Aude Billard (Invited Talk) Aude G Billard
03:10 PM Coffee Break 2 (Break)
03:30 PM Poster Session <span> <a href="#"></a> </span>
04:30 PM Enabling Robots to Communicate Reward Functions, Sandy Huang, David Held, Pieter Abbeel and Anca Dragan (Paper Presentation)
04:50 PM Hierarchical Multi-Agent Reinforcement Learning through Communicative Actions for Human-Robot Collaboration, Elena Corina Grigore and Brian Scassellati (Paper Presentation)
05:10 PM Invited Talk: Emma Brunskill (Invited Talk) Emma Brunskill
05:50 PM Panel Discussion, Closing Remarks (Discussion Panel)

Author Information

Kory Mathewson (University of Alberta)
Kaushik Subramanian (Cogitai Inc.)
Mark Ho (UC Berkeley)
Robert Loftin (North Carolina State University)
Joe L Austerweil (University of Wisconsin, Madison)

As a computational cognitive psychologist, my research program explores questions at the intersection of perception and higher-level cognition. I use recent advances in statistics and computer science to formulate ideal learner models to see how they solve these problems and then test the model predictions using traditional behavioral experimentation. Ideal learner models help us understand the knowledge people use to solve problems because such knowledge must be made explicit for the ideal learner model to successfully produce human behavior. This method yields novel machine learning methods and leads to the discovery of new psychological principles.

Anna Harutyunyan (DeepMind)
Doina Precup (McGill University / DeepMind Montreal)
Layla El Asri (Microsoft)
Matthew Gombolay (MIT)
Jerry Zhu (University of Wisconsin-Madison)
Sonia Chernova (Georgia Institute of Technology)
Charles L Isbell (Georgia Tech)
Patrick M Pilarski (University of Alberta)
Weng-Keen Wong (Oregon State University)
Manuela Veloso (Carnegie Mellon University)
Julie A Shah (MIT)
Matthew Taylor (Washington State University)
Brenna Argall (Northwestern University)
Michael Littman (Brown University)

More from the Same Authors