Kevin Lu

I am a second-year undergraduate at UC Berkeley. I work on reinforcement learning as part of the Robot Learning Lab with Professor Pieter Abbeel and Igor Mordatch.

Email  /  Resume  /  Github  /  Linkedin

profile photo
Research

My research interests lie in machine learning, reinforcement learning, artificial intelligence, statistics, and optimization. My current research focuses on harnessing uncertainty for more informed decision making, where mistakes are costly.

Adaptive Online Planning for Continual Lifelong Learning
Kevin Lu, Igor Mordatch, Pieter Abbeel
NeurIPS Deep RL, 2019   (Oral Presentation)
arXiv / website / code

Tackling reset-free learning in dynamically changing worlds by combining model-based planning with model-free learning, utilizing an expensive planner only when necessary.

Teaching
EECS

EECS 126: Probability and Random Processes
Teaching Assistant, Fall 2019

CS 70: Discrete Math and Probability
Reader, Spring 2019


Website template from Jon Barron