Accepted Papers

Oral Presentation (and Posters)

  • Enabling Robots to Communicate Reward Functions. [PDF]
    Sandy Huang, David Held, Pieter Abbeel and Anca Dragan.
  • On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems [PDF]
    Besmira Nushi, Ece Kamar, Donald Kossmann and Eric Horvitz.
  • Efficient Exploration in Monte Carlo Tree Search using Human Action Abstractions. [PDF]
    Kaushik Subramanian, Jonathan Scholz, Charles L. Isbell and Andrea L. Thomaz.
  • Hierarchical Multi-Agent Reinforcement Learning through Communicative Actions for Human-Robot Collaboration. [PDF]
    Elena Corina Grigore and Brian Scassellati.


(Spotlight 1)

  • Socratic Learning. [PDF]
    Paroma Varma, Rose Yu, Dan Iter, Chris De Sa and Christopher Re.
  • Active Reinforcement Learning: Observing Rewards at a Cost. [PDF]
    David Krueger, Owain Evans, Jan Leike and John Salvatier.
  • SPARC: an Efficient Way to Combine Reinforcement Learning and Supervised Autonomy. [PDF]
    Emmanuel Senft, Paul Baxter, Séverin Lemaignan and Tony Belpaeme.
  • Agent-Agnostic Human-in-the-Loop Reinforcement Learning. [PDF]
    David Abel, Owain Evans, John Salvatier and Andreas Stuhlmüller.
  • Analysis of a Design Pattern for Teaching with Features and Labels. [PDF]
    Christopher Meek, Patrice Simard and Jerry Zhu.
  • Probabilistic Active Learning for Active Class Selection. [PDF]
    Daniel Kottke, Georg Krempl, Marianne Stecklina, Cornelius Styp von Rekowski, Tim Sabsch, Tuan Pham Minh, Matthias Deliano, Myra Spiliopoulou and Bernhard Sick.
  • Interactive Preference Learning of Utility Functions for Multi-Objective Optimization. [PDF]
    Ian Dewancker, Michael Mccourt and Samuel Ainsworth.
  • Near-optimal Bayesian Active Learning with Correlated and Noisy Tests. [PDF]
    Yuxin Chen, Hamed Hassani and Andreas Krause.
  • Interactive User Intent Modeling for Eliciting Priors of a Normal Linear Model. [PDF]
    Iiris Sundin, Luana Micallef, Pekka Marttinen, Muhammad Ammad-Ud-Din, Tomi Peltola, Marta Soare, Giulio Jacucci and Samuel Kaski.

(Spotlight 2)

  • Probabilistic Expert Knowledge Elicitation of Feature Relevances in Sparse Linear Regression. [PDF]
    Pedram Daee, Tomi Peltola, Marta Soare and Samuel Kaski.
  • Cross-Entropy as a Criterion for Robust Interactive Learning of Latent Properties. [PDF]
    Johannes Kulick, Robert Lieck and Marc Toussaint.
  • Regression Analysis in Small-n-Large-p Using Interactive Prior Elicitation of Pairwise Similarities. [PDF]
    Homayun Afrabandpey, Tomi Peltola and Samuel Kaski.
  • Ensemble Co-Training of Image and EEG-based RSVP Classifiers for Improved Image Triage. [PDF]
    Steven Gutstein, Vernon Lawhern and Brent Lance.
  • ReVACNN: Steering Convolutional Neural Network via Real-Time Visual Analytics. [PDF]
    Sunghyo Chung, Cheonbok Park, Sangho Suh, Kyeongpil Kang, Jaegul Choo and Bum Chul Kwon.
  • Scalable batch mode Optimal Experimental Design for Deep Networks. [PDF]
    Mélanie Ducoffe and Frederic Precioso.
  • Improving Online Learning of Visual Categories by Deep Features. [PDF]
    Lydia Fischer, Stephan Hasler, Sebastian Schrom and Heiko Wersing.
  • A Multimodal Human-Robot Interaction Dataset. [PDF]
    Pablo Azagra, Yoan Mollard, Florian Golemo, Ana Cristina Murillo, Manuel Lopes and Javier Civera.
  • Training an Interactive Humanoid Robot Using Multimodal Deep Reinforcement Learning. [PDF]
    Heriberto Cuayahuitl, Guillaume Couly and Clement Olalainty.