Charles Sun

I am a M.S. student at UC Berkeley, working on deep reinforcement learning and NLP as part of the Robotic AI & Learning Lab with Professor Sergey Levine. I previously attended UC Berkeley as an undergrad and worked with Michael Janner, Coline Devin, and Glen Berseth.

Email  /  Resume  /  Github  /  LinkedIn  /  Google Scholar

profile photo

My primary research interest lies in studying and intelligent agents that can learn efficiently and safely co-exist with other intelligent agents (including humans). To this end, I am interested in reinforcement learning, natural language processing, human-computer interactions, and robotics.

Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation
Charles Sun*, Jędrzej Orbik*, Coline Devin, Brian Yang, Ahbishek Gupta, Glen Berseth, and Sergey Levine
Conference on Robot Learning (CoRL), 2021
arXiv / website / code

We propose a reinforcement learning system that can learn mobile manipulation tasks continuously in the real world without any environment instrumentation, without human intervention, and without access to privileged information, such as maps, objects positions, or a global view of the environment.


As a Teaching Assistant, I lead weekly discussion sections and hold office hours to help students.

EECS 126: Probability and Random Processes
Teaching Assistant: Spring 2021

CS 170: Efficient Algorithms and Intractable Problems
Teaching Assistant: Fall 2020

CS 61A: Structure and Interpretation of Computer Programs
Teaching Assistant: Spring 2020, Fall 2019

Website template from Jon Barron
Last updated September 2022.