Thu, Aug 15, 2019 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Xusen Yin, USC/ISI
Talk Title: COMPREHENSIBLE CONTEXT-DRIVEN TEXT GAME PLAYING
Series: Natural Language Seminar
Abstract: In order to train a computer agent to play a text based computer game, we must represent each hidden state of the game. A Long Short Term Memory LSTM model running over observed texts is a common choice for state construction. However, a normal Deep Q learning Network DQN for such an agent requires millions of steps of training or more to converge. As such, an LSTM based DQN can take tens of days to finish the training process. Though we can use a Convolutional Neural Network CNN as a text encoder to construct states much faster than the LSTM, doing so without an understanding of the syntactic context of the words being analyzed can slow convergence. In this paper, we use a fast CNN to encode position and syntax-oriented structures extracted from observed texts as states. We additionally augment the reward signal in a universal and practical manner. Together, we show that our improvements can not only speed up the process by one order of magnitude but also learn a superior agent.
Biography: Xusen Yin is a 3rd-year Ph.D. student in USC ISI, advised by Dr. Jonathan May.
Host: Xusen Yin and Jon May
More Info: https://nlg.isi.edu/nl-seminar
WebCast Link: https://bluejeans.com/s/qXurz
Audiences: Everyone Is Invited
Contact: Peter Zamar