research
∙
07/10/2023
Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data
In some applications of reinforcement learning, a dataset of pre-collect...
share
research
∙
11/10/2022
When is Realizability Sufficient for Off-Policy Reinforcement Learning?
Model-free algorithms for reinforcement learning typically require a con...
research
∙
06/01/2022
Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning
The Q-learning algorithm is a simple and widely-used stochastic approxim...
research
∙
03/24/2022
Bellman Residual Orthogonalization for Offline Reinforcement Learning
We introduce a new reinforcement learning principle that approximates th...
research
∙
08/19/2021
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning
Actor-critic methods are widely used in offline reinforcement learning p...
research
∙
07/21/2021
Design of Experiments for Stochastic Contextual Linear Bandits
In the stochastic linear contextual bandit setting there exist several m...
research
∙
03/24/2021
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
Policy optimization methods are popular reinforcement learning algorithm...
research
∙
12/14/2020
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL
Several practical applications of reinforcement learning involve an agen...
research
∙
08/18/2020
Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration
There has been growing progress on theoretical analyses for provably eff...
research
∙
02/29/2020
Learning Near Optimal Policies with Low Inherent Bellman Error
We study the exploration problem with approximate linear action-value fu...
research
∙
11/03/2019
Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
In order to make good decision under uncertainty an agent must learn fro...
research
∙
11/01/2019
Frequentist Regret Bounds for Randomized Least-Squares Value Iteration
We consider the exploration-exploitation dilemma in finite-horizon reinf...
research
∙
01/01/2019
Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
Strong worst-case performance bounds for episodic reinforcement learning...
research
∙
11/25/2018