Skip to main navigation
Skip to search
Skip to main content
Princeton University Home
Help & FAQ
Home
Profiles
Research units
Facilities
Projects
Research output
Press/Media
Search by expertise, name or affiliation
Near-Optimal Representation Learning for Linear Bandits and Linear RL
Jiachen Hu
, Xiaoyu Chen
,
Chi Jin
, Lihong Li
, Liwei Wang
Electrical and Computer Engineering
Princeton Language and Intelligence (PLI)
Research output
:
Chapter in Book/Report/Conference proceeding
›
Conference contribution
39
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Near-Optimal Representation Learning for Linear Bandits and Linear RL'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Near-optimal
100%
Regret
100%
Multi-task
100%
Optimal Representation
100%
Representation Learning
100%
Linear Bandits
100%
Linear Function Approximation
66%
Sampling Efficiency
33%
Bandit Problems
33%
Function Approximation
33%
Shared Representations
33%
Bellman
33%
Linear Representation
33%
Bandits
33%
Multi-Task Representation Learning
33%
Computer Science
Function Approximation
100%
Representation Learning
100%
Optimal Representation
100%
Efficient Algorithm
33%
Linear Representation
33%
Mathematics
Approximation Function
100%
Representation Learning
100%
Function Value
66%