activity
20182021
most citedProvable Benefits of Actor-Critic Methods for Offline Reinforcement Learning

14 citations · 21 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2023

Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data

Ruiqi Zhang, Andrea Zanette

In some applications of reinforcement learning, a dataset of pre-collected experience is already available but it is also possible to acquire some additional online data to help im…

cs.LG202114 cited

Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning

Andrea Zanette, Martin J. Wainwright, Emma Brunskill

Actor-critic methods are widely used in offline reinforcement learning practice, but are not so well-understood theoretically. We propose a new offline actor-critic algorithm that…

cs.LG20213 cited

Design of Experiments for Stochastic Contextual Linear Bandits

Andrea Zanette, Kefan Dong, Jonathan Lee +1

In the stochastic linear contextual bandit setting there exist several minimax procedures for exploration with policies that are reactive to the data being acquired. In practice, t…

cs.LG2021

Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation

Andrea Zanette, Ching-An Cheng, Alekh Agarwal

Policy optimization methods are popular reinforcement learning algorithms, because their incremental and on-policy nature makes them more stable than the value-based counterparts.…

cs.LG2020

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL

Andrea Zanette

Several practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require u…

cs.LG2020

Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration

Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer +1

There has been growing progress on theoretical analyses for provably efficient learning in MDPs with linear function approximation, but much of the existing work has made strong as…