Loading…
Attending this event?
Monday, October 14 • 4:45pm - 5:00pm
Imitate Like a Baby: The Key to Efficient Exploration in Deep Reinforcement Learning

Sign up or log in to save this to your schedule and see who's attending!

Mimicking the behavior of an expert player in a Reinforcement Learning (RL) Environment to enhance the training of a novice agent from scratch is called Imitation Learning (IL). In most RL environments, the state sequences an agent encounters is a Markov Decision Process. This makes mimicking difficult as it is unlikely that a new agent may encounter similar state sequences as an expert. Prior research in IL proposes to learn a mapping between expert's states and actions, needing considerable number of state-action pairs to achieve good results. We propose an alternative to IL by appending the novice's action space with frequent action sequences of the expert. This modification improves the exploration and significantly outperforms alternatives like Dataset-Aggregation. We experiment with popular Atari games and show significant and consistent growth in the score that the new agents achieve using just a few expert action sequences.

Speakers
TM

Tharun Medini

Rice University
avatar for Anshumali Shrivastava

Anshumali Shrivastava

Presenter, Rice University
Anshumali Shrivastava is an Assistant Professor in the Department of Computer Science at Rice University with joint appointments in Statistics and ECE department. His broad research interests include large scale machine learning, randomized algorithms for big data systems and... Read More →



Monday October 14, 2019 4:45pm - 5:00pm
BRC 103

Attendees (5)