255 citations · 2.4k across the 127 of their papers we have counts for
101 papers · 1 filter
On the Two Faces of Adam in Separable Linear Classification
Chen Fan, Csaba Szepesvári
We consider the behavior of deterministic, full-batch, bias-corrected Adam in separable linear classification with softmax parametrization under log-loss. In this setting, under a…
Stochastic Gradient Succeeds for Bandits
Jincheng Mei, Zixin Zhong, Bo Dai +3
We show that the \emph{stochastic gradient} bandit algorithm converges to a \emph{globally optimal} policy at an rate, even with a \emph{constant} step size. Remarkably, g…
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation
Philip Amortila, Nan Jiang, Csaba Szepesvári
Theoretical guarantees in reinforcement learning (RL) are known to suffer multiplicative blow-up factors with respect to the misspecification error of function approximation. Yet,…
Context-lumpable stochastic bandits
Chung-Wei Lee, Qinghua Liu, Yasin Abbasi-Yadkori +3
We consider a contextual bandit problem with contexts and actions. In each round , the learner observes a random context and chooses an action based on its pas…
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang +12
Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-regularized reinforcement learning (RL), has served as the basis for recent high-performi…
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
Qinghua Liu, Gellért Weisz, András György +2
While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy opti…