Ayush Jain

I am a Computer Science PhD student in at University of Southern California, co-advised by Prof. Joseph J. Lim and Prof. Erdem Bıyık. My research interests include Reinforcement Learning, Deep Learning, and Robotics.

I was fortunate to intern at Microsoft Research, Montreal and Naver AI, Seoul. Before joining USC, I spent two great years in Seoul, working at Samsung Research Korea. Earlier, I graduated from IIT Delhi, where I worked under the guidance of Prof. Sumeet Agarwal and Prof. Rajakrishnan Rajkumar.

Email  |  Twitter  |  CV  |  Google Scholar  |  LinkedIn

I am primarily interested in giving artificial agents the ability to think, understand and act in novel circumstances. My research involves using reinforcement learning and representation learning to achieve generalizable and adaptable agents for reasoning, recommender systems, and robotics.

Sharing behaviors between tasks to improve exploration for multitask reinforcement learning.

For optimal decision-making under a varying action space, we learn the relations between the available actions using a graph-attention network based policy architecture.

Our proposed RL framework enables agents to solve sequential decision-making tasks even when the available actions (tools or skills) have not been seen before.

This work investigates the extent to which word order choices in Hindi language are influenced by the drive to minimize the information variance in a sentence.

Course: Deep Learning and its Applications
Teaching Assistant (USC)

CSCI566 - Fall 2020

CSCI566 - Fall 2019

CSCI599 - Spring 2019

Credits to the Coolest template!