Login
Talks & Seminars
Title: Towards Creating Agents that Learn
Dr. Shivaram Kalyanakrishnan, Yahoo! Labs
Date & Time: April 9, 2014 15:00
Venue: Conference Room, C Block, 01st Floor, Department of Computer Science and Engineering, Kanwal Rekhi Building
Abstract:
As a computer scientist with a specialisation in artificial intelligence, my research is motivated by the goal of creating intelligent agents, especially ones that learn. I will begin this talk with a brief overview of my research efforts on related topics, including sequential decision making, humanoid robotics, and computational advertising. Subsequently I will present in detail a recent line of work on the topic of exploration, as instantiated through multi-armed bandits. Specifically we consider the problem of selecting, from among n real-valued random variables, a subset of size m of those with the highest means, based on efficiently sampling the random variables. Formalising this problem under the PAC setting, we design algorithms to minimise the sample complexity of exploration. Theoretical analysis and experiments both demonstrate the efficiency of our algorithms.
Speaker Profile:
Shivaram Kalyanakrishnan is a Research Scientist at Yahoo Labs Bangalore. His primary research interests lie in the fields of artificial intelligence and machine learning, spanning areas such as reinforcement learning, agents and multiagent systems, humanoid robotics, multi-armed bandits, and on-line advertising. He obtained his Ph.D. in Computer Science from the University of Texas at Austin (2011), and his B.Tech. in Computer Science and Engineering from the Indian Institute of Technology Madras (2004). He has extensively used robot soccer as a test domain for his research, and has actively contributed to initiatives such as RoboCup and the Reinforcement Learning competitions.
List of Talks

Webmail

Username:
Password:
Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback