R255 Imitation Learning
Imitation learning was initially proposed in robotics as a way to better robots (Schaal, 1999). The connecting theme is to combine the reward function in the end of the action sequence with demonstrations of the task in hand by an expert. Since then it has been applied to a number of tasks which can be modelled as a sequence of actions taken by an agent. These include the video game agents, moving cameras to track players and structured prediction in various tasks in natural language processing. For a recent tutorial see here.
Over the years there has been a number of algorithms proposed, in the literature but without necessarily making the connections between the various approaches clear. The initial lecture will set the criteria to be used to examine the algorithms with.
Each student will present a paper and corresponding algorithm from the list of papers below and may write a report testing it on a dataset of their choice.
Search-based Structured Prediction Hal Daumé III, John Langford and Daniel Marcu Machine Learning Journal (MLJ), 2009
A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning Stephane Ross, Geoffrey J. Gordon, J. Andrew Bagnell Artificial Intelligence and Statistics Conference (AISTATS), 2011
Learning to search better than your teacher Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daumé III and John Langford International Conference on Machine Learning (ICML), 2015
Sequence Level Training with Recurrent Neural Networks Marc’Aurelio Ranzato, Sumit Chopra, Michael Auli, Wojciech Zaremba International Conference on Machine Learning (ICLR), 2016
Generative Adversarial Imitation Learning Jonathan Ho and Stefano Ermon Neural Information Processing Systems (NeurIPS) 2016