activity
20172025
most citedDon't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning

21 citations · 87 across the 19 of their papers we have counts for

collaborators
Showing 2019Show all

2 papers · 1 filter

cs.LG2019★ 17 cited

Frequentist Regret Bounds for Randomized Least-Squares Value Iteration

Andrea Zanette, David Brandfonbrener, Emma Brunskill +2

We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning (RL). When the state space is large or continuous, traditional tabular approaches are unfe…

cs.LG2019★ 8 cited

Geometric Insights into the Convergence of Nonlinear TD Learning

David Brandfonbrener, Joan Bruna

While there are convergence guarantees for temporal difference (TD) learning when using linear function approximators, the situation for nonlinear models is far less understood, an…