Skip to main navigation
Skip to search
Skip to main content
Illinois Experts Home
LOGIN & Help
Home
Profiles
Research units
Research & Scholarship
Datasets
Honors
Press/Media
Activities
Search by expertise, name or affiliation
Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison
Tengyang Xie,
Nan Jiang
Siebel School of Computing and Data Science
Electrical and Computer Engineering
Research output
:
Contribution to journal
›
Conference article
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Approximation Scheme
100%
Batch Data
50%
Batch Reinforcement Learning
100%
Bellman
100%
Classical Algorithm
50%
Double Sampling
50%
Error Estimates
50%
Error Propagation
50%
Fitted Q-iteration
50%
Importance Weighting
50%
Iterative Methods
50%
Performance Guarantee
50%
Performance Loss
50%
Squared Loss
50%
Stationary Policy
50%
Theoretical Comparison
100%
Mathematics
Distinct Characteristic
100%
Iterative Method
100%
Stationary Policy
100%
Engineering
Batch Data
50%
Error Estimation
50%
Performance Loss
50%
Reinforcement Learning
100%
Chemical Engineering
Reinforcement Learning
100%
Earth and Planetary Sciences
Error Propagation
100%