Mark Rowland
Research Scientist | Google DeepMind
Research Scientist | Google DeepMind
I'm a research scientist at Google DeepMind, where I work on reinforcement learning. I enjoy working on a wide spectrum of problems, from developing theoretical guarantees for new algorithms through to large-scale applications of deep reinforcement learning.
Current highlighted projects
AlphaProof
Blog post
An Analysis of Quantile Temporal-Difference Learning
Mark Rowland, Rémi Munos, Mohammad Gheshlaghi Azar, Yunhao Tang, Georg Ostrovski, Anna Harutyunyan, Karl Tuyls, Marc G. Bellemare, Will Dabney
Establishes convergence of quantile temporal-difference learning with probability 1, through stochastic approximation of differential inclusions and connections to quantile dynamic programming.
JMLR 2024 | arXiv version | To be presented at ICML 2025
Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
Mark Rowland, Li Kevin Wenliang, Rémi Munos, Clare Lyle, Yunhao Tang, Will Dabney
How many samples do you need to accurately estimate the return distribution of a given policy? This paper shows that, roughly speaking, no more are required than for estimating just the value function of the policy.
NeurIPS 2024 | arXiv version
See my Google Scholar page for full details of publications and preprints.
Contact
firstnamelastname [at] google [dot] com