Schedule


08:30 AM - Introduction

08:35 AM - Talk from Organizers: Teaching Machines like We Teach People

Igor Labutov

09:00 AM - Invited Talk: Mapping Navigation Instructions to Continuous Control

Yoav Artzi

09:30 AM - Invited Talk: An Cognitive Architecture Approach to Interactive Task Learning

John Laird

10:00 AM - Contributed Talk: Compositional Imitation Learning: Explaining and executing one task at a time. pdf

Thomas Kipf, Yujia Li, Hanjun Dai, Vinicius Zambaldi, Edward Grefenstette, Pushmeet Kohli and Peter Battaglia

10:15 AM - Contributed Talk: Learning to Learn from Imperfect Demonstrations. pdf

Ge Yang and Chelsea Finn


Coffee Break from 10:30- 11 AM


11:00 AM - Invited Talk: Natural Language Supervision

Percy Liang

11:30 AM - Invited Talk: Control Algorithms for Imitation Learning from Observation

Peter Stone

12:00 PM - Contributed talk: From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following. pdf

Justin Fu, Anoop Korattikara, Sergey Levine and Sergio Guadarrama

12:15 PM - Contributed Talk: Teaching Multiple Tasks to an RL Agent using LTL . pdf

Rodrigo Toro Icarte, Toryn Q. Klassen, Richard Valenzano and Sheila McIlraith

Lunch Break from 12:30- 1:30 PM


1:30 PM - Invited Talk: Meta-Learning to Follow Instructions, Examples, and Demonstrations

Sergey Levine

2:00 PM - Invited Talk: Learning to Understand Natural Language Instructions through Human-Robot Dialog

Raymond Mooney

2:30 PM - Contributed Talk: The Implicit Preference Information in an Initial State . pdf

Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel and Anca Dragan

2:45 PM - Contributed Talk: Modelling User's Theory of AI's Mind in Interactive Intelligent Systems. pdf

Tomi Peltola, Mustafa Mert Çelikok, Pedram Daee and Samuel Kaski


3:30 PM - 4:15 PM : Poster Session

Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing. pdf

Carolin Lawrence and Stefan Riezler

Teacher-Student Adaptation for Video Segmentation via Human Robot Interaction (HRI). pdf

Mennatullah Siam, Chen Jiang, Steven Lu, Laura Petrich, Mahmoud Gamal, Mohamed ElHoseiny and Martin Jagersand

What Would pi* Do?: Imitation Learning via Off-Policy Reinforcement Learning. pdf

Siddharth Reddy, Anca Dragan and Sergey Levine

Using Natural Language Descriptions to Guide Zero-Shot Image Classification: A Meta-Learning Approach. pdf

R. Lily Hu, Caiming Xiong and Richard Socher

Teaching with IMPACT . pdf

Carl Trimbach and Michael Littman

Meta-Learning Language-Guided Policy Learning. pdf

John Co-Reyes, Abhishek Gupta, Suvansh Sanjeev, Nick Altieri, John DeNero, Pieter Abbeel and Sergey Levine

Training an Interactive Helper. pdf

Mark Woodward, Chelsea Finn and Karol Hausman

Learning a Multi-Modal Policy via Imitating Demonstrations with Mixed Behaviors. pdf

Fang-I Hsiao, Jui-Hsuan Kuo and Min Sun

Advice-Based Exploration in Model-Based Reinforcement Learning. pdf

Rodrigo Toro Icarte, Toryn Q. Klassen, Richard Valenzano and Sheila McIlraith

Reward-adjusted diameters of a Markov decision process and their conditioning by potential-based reward shaping. pdf

Falcon Z. Dai and Matthew Walter

Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning. pdf

Aishwarya Agrawal, Mateusz Malinowski, Felix Hill, Ali Eslami, Oriol Vinyals and Tejas Kulkarni

Towards an IDE for agent design. pdf

Matthew Rahtz, James Fang, Anca Dragan and Dylan Hadfield-Menell

Investigating Machine-Learning Interaction with Wizard-of-Oz Experiments. pdf

Rob Sheline and Chris MacLellan

One-shot Semantic Parsing. pdf

Brian Lu, Igor Labutov, Bishan Yang, Tom Mitchell


4:15 PM - Contributed Talk: Assisted Inverse Reinforcement Learning . pdf

Parameswaran Kamalaruban, Rati Devidze, Teresa Yeo, Trisha Mittal, Volkan Cevher and Adish Singla

4:30 PM - Invited Talk: Teaching through Dialogue and Games

Jason Weston


Panel discussion from 5 PM - 5:45 PM

Panel: Yoav Artzi, Percy Liang, Ray Mooney, Peter Stone, Jason Weston