Liu Weiwei

Welcome!

I just completed my Ph.D in Computer Science at Brown University, where I was fortunate to be advised by Prof. Michael Littman.

News

• Fall 2020 I will be joining DeepMind London as a Research Scientist!
• June 26: New ICML paper out on affordances in RL.
• April 27: My dissertation is done!
• April 7: I defended my thesis!
• March 1: New AISTATS paper out on state-action abstraction.
• February 1: New AAAI paper out on understanding human planning.
• December 15: Notes from NeurIPS 2019 available.
• December 8-14: At NeurIPS to give a talk (slides, video) at the Meta-Learning workshop .

Interests

My research focuses on bringing mathematical clarity to the central philosophical questions surrounding computation and learning.

I'm currently interested in understanding abstraction and its role in agency. I study how rational agents model the worlds they inhabit, focusing on the representational practices that underly effective learning and planning. I typically work with the reinforcement learning problem, drawing on tools and ideas from computational learning theory, computational complexity, analytic philosophy, and information theory.

I also care deeply about the mission of computational sustainability.

Featured Work

	A Theory of Abstraction in Reinforcement Learning Ph.D Thesis, 2020 My dissertation, aimed at understanding abstraction and its role in effective reinforcement learning. Advised by Michael L. Littman.
	Value Preserving State-Action Abstractions AISTATS 2020 We prove which combinations of state abstractions and options are guaranteed to preserve representation of near-optimal policies in any finite Markov Decision Process. Joint work with Nathan Umabnhowar, Khimya Khetarpal, Dilip Arumugam, Doina Precup, and Michael L. Littman.
	The Efficiency of Human Cognition Reflects Planned Use of Information Processing AAAI 2020 We develop a model that characterizes the planned use of information processing as a meta-reasoning problem and study this model's capacity to predict human reaction times in simple tasks. By Mark K. Ho, myself, Jonathan D. Cohen, Michael L. Littman, Thomas L. Griffiths.
	The Value of Abstraction Current Opinions in Behavioral Science 2019 We discuss the vital role that abstraction plays in efficient decision making. By Mark K. Ho, myself, Michael L. Littman, Thomas L. Griffiths.
	The Expected-Length Model of Options IJCAI 2019 We introduce and motivate the Expected-Length Model of Options, a simpler alternative for characterizing the transition and reward functions of options. Joint with John Winder, Marie desJardins, and Michael L. Littman.
	State Abstraction as Compression in Apprenticeship Learning AAAI 2019 We study state abstractions that trade-off between compression and optimality through rate-distortion theory. Joint work with Dilip Arumugam, Kavosh Asadi, Yuu Jinnai, Michael L. Littman, and Lawson L.S. Wong.
	Finding Options that Minimize Planning Time ICML 2019 We prove that the problem of finding options that minimize planning time is NP-Hard. By Yuu Jinnai, myself, D Ellis Hershkowitz, Michael L. Littman, and George Konidaris.

Personal

For fun, I'm a big fan of basketball, snowboarding, baking, games, and music (I play violin/guitar and mostly listen to progressive metal).

I'm an advocate of a few specific causes: sustainability efforts, existential risk minimization, space exploration, and improving the diversity, quality, and accessibility of education.

Always up for a chat -- shoot me an email if you'd like to discuss anything!