b'Ruosong Wang'

research

∙ 02/22/2023

Provably Efficient Reinforcement Learning via Surprise Bound

Value function approximation is important in modern reinforcement learni...

0 Hanlin Zhu, et al. ∙

research

∙ 10/20/2022

Horizon-Free Reinforcement Learning for Latent Markov Decision Processes

We study regret minimization for reinforcement learning (RL) in Latent M...

0 Runlong Zhou, et al. ∙

research

∙ 05/26/2022

Variance-Aware Sparse Linear Bandits

It is well-known that the worst-case minimax regret for sparse linear ba...

0 Yan Dai, et al. ∙

research

∙ 11/01/2021

Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning

Recently there is a surge of interest in understanding the horizon-depen...

0 Yuanzhi Li, et al. ∙

research

∙ 06/14/2021

Online Sub-Sampling for Reinforcement Learning with General Function Approximation

Designing provably efficient algorithms with general function approximat...

0 Dingwen Kong, et al. ∙

research

∙ 03/23/2021

An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap

A fundamental question in the theory of reinforcement learning is: suppo...

0 Yuanhao Wang, et al. ∙

research

∙ 03/19/2021

Bilinear Classes: A Structural Framework for Provable Generalization in RL

This work introduces Bilinear Classes, a new structural framework, which...

52 Simon S. Du, et al. ∙

research

∙ 03/08/2021

Instabilities of Offline RL with Pre-Trained Neural Representation

In offline reinforcement learning (RL), we seek to utilize offline data ...

15 Ruosong Wang, et al. ∙

research

∙ 10/22/2020

What are the Statistical Limits of Offline RL with Linear Function Approximation?

Offline reinforcement learning seeks to utilize offline (observational) ...

0 Ruosong Wang, et al. ∙

research

∙ 10/22/2020

Planning with Submodular Objective Functions

We study planning with submodular objective functions, where instead of ...

0 Ruosong Wang, et al. ∙

research

∙ 06/19/2020

On Reward-Free Reinforcement Learning with Linear Function Approximation

Reward-free reinforcement learning (RL) is a framework which is suitable...

0 Ruosong Wang, et al. ∙

research

∙ 06/16/2020

Preference-based Reinforcement Learning with Finite-Time Guarantees

Preference-based Reinforcement Learning (PbRL) replaces reward values in...

0 Yichong Xu, et al. ∙

research

∙ 06/15/2020

Nearly Linear Row Sampling Algorithm for Quantile Regression

We give a row sampling algorithm for the quantile loss function with sam...

0 Yi Li, et al. ∙

research

∙ 05/21/2020

Provably Efficient Reinforcement Learning with General Value Function Approximation

Value function approximation has demonstrated phenomenal empirical succe...

13 Ruosong Wang, et al. ∙

research

∙ 05/01/2020

Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?

Learning to plan for long horizons is a central challenge in episodic re...

7 Ruosong Wang, et al. ∙

research

∙ 03/15/2020

Provably Efficient Exploration for RL with Unsupervised Learning

We study how to use unsupervised learning for efficient exploration in r...

2 Fei Feng, et al. ∙

research

∙ 02/17/2020

Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity

The current paper studies the problem of agnostic Q-learning with functi...

0 Simon S. Du, et al. ∙

research

∙ 12/09/2019

Optimism in Reinforcement Learning with Generalized Linear Function Approximation

We design a new provably efficient algorithm for episodic reinforcement ...

0 Yining Wang, et al. ∙

research

∙ 11/03/2019

Enhanced Convolutional Neural Tangent Kernels

Recent research shows that for training with ℓ_2 loss, convolutional neu...

17 Zhiyuan Li, et al. ∙

research

∙ 10/30/2019

Continuous Control with Contexts, Provably

A fundamental challenge in artificial intelligence is to build an agent ...

0 Simon S. Du, et al. ∙

research

∙ 10/07/2019

Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?

Modern deep learning methods provide an effective means to learn good re...

15 Simon S. Du, et al. ∙

research

∙ 10/04/2019

Efficient Symmetric Norm Regression via Linear Sketching

We provide efficient algorithms for overconstrained linear regression pr...

0 Zhao Song, et al. ∙

research

∙ 10/03/2019

Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

Recent research shows that the following two models are equivalent: (a) ...

16 Sanjeev Arora, et al. ∙

research

∙ 06/14/2019

Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle

Q-learning with function approximation is one of the most popular method...

0 Simon S. Du, et al. ∙

research

∙ 06/13/2019

The Communication Complexity of Optimization

We consider the communication complexity of a number of distributed opti...

0 Santosh S. Vempala, et al. ∙

research

∙ 05/30/2019

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

While graph kernels (GKs) are easy to train and enjoy provable theoretic...

4 Simon S. Du, et al. ∙

research

∙ 05/14/2019

Dimensionality Reduction for Tukey Regression

We give the first dimensionality reduction methods for the overconstrain...

0 Kenneth L. Clarkson, et al. ∙

research

∙ 04/26/2019

On Exact Computation with an Infinitely Wide Neural Net

How well does a classic deep net architecture like AlexNet or VGG19 clas...

0 Sanjeev Arora, et al. ∙

research

∙ 04/11/2019

Tight Bounds for the Subspace Sketch Problem with Applications

In the subspace sketch problem one is given an n× d matrix A with O((nd)...

0 Yi Li, et al. ∙

research

∙ 01/24/2019

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Recent works have cast some light on the mystery of why deep nets fit an...

16 Sanjeev Arora, et al. ∙

research

∙ 11/19/2018

Classical Algorithms from Quantum and Arthur-Merlin Communication Protocols

The polynomial method from circuit complexity has been applied to severa...

0 Lijie Chen, et al. ∙

research

∙ 01/13/2018

Tight Bounds for ℓ_p Oblivious Subspace Embeddings

An ℓ_p oblivious subspace embedding is a distribution over r × n matrice...

0 Ruosong Wang, et al. ∙

research

∙ 06/04/2017

Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration

We study the combinatorial pure exploration problem Best-Set in stochast...

0 Lijie Chen, et al. ∙

Ruosong Wang

Featured Co-authors