Kevin Lu

I am a third-year undergraduate studying EECS at UC Berkeley. I work on reinforcement learning, decision making, and artificial intelligence as part of the Robot Learning Lab where I am fortunate to work with Igor Mordatch, Aditya Grover, and Pieter Abbeel. I am the head TA of EECS 126, Berkeley's class on probability and random processes.

Email  /  Resume  /  Google Scholar  /  Github

profile photo

I am broadly interested in artificial intelligence. I am particularly interested in making learning more autonomous, such as enabling agents to learn in reset-free, nonstationary, or unsupervised settings; or by incorporating more sources of supervision, such as offline or multimodal data.

Pretrained Transformers as Universal Computation Engines
Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch
arXiv preprint, 2021
arXiv / blog / code
unofficial: press / video (by Yannic Kilcher)

We show that a transformer pretrained on natural language can, without finetuning of the self-attention and feedforward layers, match the performance of a transformed fully trained on a downstream non-language modality.

Reset-Free Lifelong Learning with Skill-Space Planning
Kevin Lu, Aditya Grover, Pieter Abbeel, Igor Mordatch
International Conference on Learning Representations, 2021
NeurIPS Deep RL Workshop, 2020   (Contributed Talk)
arXiv / website / oral / poster / code

We show planning over a space of skills is a key component of successful reset-free lifelong learning, avoiding sink states, improving stability, and increasing learning signal.

Efficient Empowerment Estimation for Unsupervised Stabilization
Ruihan Zhao, Kevin Lu, Pieter Abbeel, Stas Tiomkin
International Conference on Learning Representations, 2021

We design a new unbiased empowerment estimator and show it represents empowerment more faithfully than traditional variational mutual information algorithms.

Adaptive Online Planning for Continual Lifelong Learning
Kevin Lu, Igor Mordatch, Pieter Abbeel
NeurIPS Deep RL Workshop, 2019   (Contributed Talk)
arXiv / website / oral / poster / 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.


EECS 126: Probability and Random Processes
Head Teaching Assistant: Spring 2021, Fall 2020
Teaching Assistant: Spring 2020, Fall 2019

CS 70: Discrete Math and Probability
Reader: Spring 2019

Website template from Jon Barron