( events)   Timezone: »  
Workshop
Sat Dec 08 05:00 AM -- 03:30 PM (PST) @ Room 516 AB
Learning by Instruction
Shashank Srivastava · Igor Labutov · Bishan Yang · Amos Azaria · Tom Mitchell





Today machine learning is largely about pattern discovery and function approximation. But as computing devices that interact with us in natural language become ubiquitous (e.g., Siri, Alexa, Google Now), and as computer perceptual abilities become more accurate, they open an exciting possibility of enabling end-users to teach machines similar to the way in which humans teach one another. Natural language conversation, gesturing, demonstrating, teleoperating and other modes of communication offer a new paradigm for machine learning through instruction from humans. This builds on several existing machine learning paradigms (e.g., active learning, supervised learning, reinforcement learning), but also brings a new set of advantages and research challenges that lie at the intersection of several fields including machine learning, natural language understanding, computer perception, and HCI.

The aim of this workshop is to engage researchers from these diverse fields to explore fundamental research questions in this new area, such as:
How do people interact with machines when teaching them new learning tasks and knowledge?
What novel machine learning models and algorithms are needed to learn from human instruction?
What are the practical considerations towards building practical systems that can learn from instruction?

Introduction (Welcome)
Teaching Machines like we Teach People (Talk from Organizers)
Mapping Navigation Instructions to Continuous Control (Invited Talk)
An Cognitive Architecture Approach to Interactive Task Learning (Invited Talk)
Compositional Imitation Learning: Explaining and executing one task at a time (Contributed Talk)
Learning to Learn from Imperfect Demonstrations (Contributed Talk)
Natural Language Supervision (Invited Talk)
Control Algorithms for Imitation Learning from Observation (Invited Talk)
From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following (Contributed talk)
Teaching Multiple Tasks to an RL Agent using LTL (Contributed Talk)
Meta-Learning to Follow Instructions, Examples, and Demonstrations (Invited Talk)
Learning to Understand Natural Language Instructions through Human-Robot Dialog (Invited Talk)
The Implicit Preference Information in an Initial State (Contributed Talk)
Modelling User's Theory of AI's Mind in Interactive Intelligent Systems (Contributed Talk)
Poster Session
Assisted Inverse Reinforcement Learning (Contributed Talk)
Teaching through Dialogue and Games (Invited Talk)
Panel Discussion (Discussion Panel)