104 citations · 270 across the 46 of their papers we have counts for
6 papers · 1 filter
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
Dylan J. Foster, Noah Golowich, Jian Qian +2
We consider the problem of interactive decision making, encompassing structured bandits and reinforcement learning with general function approximation. Recently, Foster et al. (202…
STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games
Constantinos Daskalakis, Noah Golowich, Stratis Skoulakis +1
Min-max optimization problems involving nonconvex-nonconcave objectives have found important applications in adversarial training and other multi-agent learning settings. Yet, no k…
Learning in Observable POMDPs, without Computationally Intractable Oracles
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
Much of reinforcement learning theory is built on top of oracles that are computationally hard to implement. Specifically for learning near-optimal policies in Partially Observable…
The Complexity of Markov Equilibrium in Stochastic Games
Constantinos Daskalakis, Noah Golowich, Kaiqing Zhang
We show that computing approximate stationary Markov coarse correlated equilibria (CCE) in general-sum stochastic games is computationally intractable, even when there are two play…
Smoothed Online Learning is as Easy as Statistical Learning
Adam Block, Yuval Dagan, Noah Golowich +1
Much of modern learning theory has been split between two regimes: the classical offline setting, where data arrive independently, and the online setting, where data arrive adversa…
Planning in Observable POMDPs in Quasipolynomial Time
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
Partially Observable Markov Decision Processes (POMDPs) are a natural and general model in reinforcement learning that take into account the agent's uncertainty about its current s…