A Free Lunch from the Noise: Provable and Practical Exploration for
Representation Learning

v1v2 (latest)

A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning

22 November 2021

Tianjun Zhang

Csaba Szepesvári

ArXiv (abs)PDF HTML

Papers citing "A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning"

9 / 9 papers shown

Title
AmorLIP: Efficient Language-Image Pretraining via Amortization Haotian Sun Yitong Li Yuchen Zhuang Niao He Hanjun Dai Bo Dai VLM 86 0 0 25 May 2025
RLHF from Heterogeneous Feedback via Personalization and Preference Aggregation Chanwoo Park Mingyang Liu Dingwen Kong Kaiqing Zhang Asuman Ozdaglar 141 41 0 30 Apr 2024
Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding Zhaolin Ren Tongzheng Ren Haitong Ma Na Li Bo Dai 107 10 0 08 Apr 2023
Latent Variable Representation for Reinforcement Learning Zhaolin Ren Chenjun Xiao Tianjun Zhang Na Li Zhaoran Wang Sujay Sanghavi Dale Schuurmans Bo Dai OffRL 102 10 0 17 Dec 2022
Leveraging Offline Data in Online Reinforcement Learning Andrew Wagenmaker Aldo Pacchiano OffRL OnRL 103 41 0 09 Nov 2022
Spectral Decomposition Representation for Reinforcement Learning Zhaolin Ren Tianjun Zhang Lisa Lee Joseph E. Gonzalez Dale Schuurmans Bo Dai OffRL 98 29 0 19 Aug 2022
Making Linear MDPs Practical via Contrastive Representation Learning Tianjun Zhang Zhaolin Ren Mengjiao Yang Joseph E. Gonzalez Dale Schuurmans Bo Dai 74 44 0 14 Jul 2022
Provable Benefits of Representational Transfer in Reinforcement Learning Alekh Agarwal Yuda Song Wen Sun Kaiwen Wang Mengdi Wang Xuezhou Zhang OffRL 102 35 0 29 May 2022
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach Xuezhou Zhang Yuda Song Masatoshi Uehara Mengdi Wang Alekh Agarwal Wen Sun OffRL 125 58 0 31 Jan 2022

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.