Prasanna, better known as PP. I completed my undergrad in 2012 in Computer Science and Engineering at SASTRA University, Tanjore.
I am pursuing my First year of MS under Prof. Ravindran Balaraman. You can contact me at [email@example.com]
Probabilistic Reasoning in AI
Natural Language Processing
Reinforcement Learning (Currently Doing)
Planning and Constraint Satisfaction (Currently Doing)
What am I interested in?
Reinforcement Learning, Bayesian Reinforcement Learning and Deep Learning.
Overview of Research
My motivation in research is to make the learning phase of an agent efficient. I am trying to understand the nature of agents trying
to learn to behave optimally in an unknown environment.
Prasanna P, Sarath Chandar A P, and Ravindran B, iBayes: A Thompson Sampling Approach to Reinforcement Learning with Instructions
Presented at the NIPS workshop on Novel Trends and Applications in Reinforcement Learning 2014.