André Biedenkapp

About André Biedenkapp

André Biedenkapp, With an exceptional h-index of 16 and a recent h-index of 16 (since 2020), a distinguished researcher at Albert-Ludwigs-Universität Freiburg, specializes in the field of Dynamic Algorithm Configuration, Learning to Learn, Deep Reinforcement Learning, AutoML, AutoRL.

His recent articles reflect a diverse array of research interests and contributions to the field:

Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning

Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization

Hierarchical Transformers are Efficient Meta-Reinforcement Learners

MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning

Contextualize Me--The Case for Context in Reinforcement Learning

Gray-Box Gaussian Processes for Automated Reinforcement Learning

Automated Dynamic Algorithm Configuration

AutoRL-Bench 1.0

André Biedenkapp Information

University

Position

PhD candidate

Citations(all)

907

Citations(since 2020)

888

Cited By

111

hIndex(all)

16

hIndex(since 2020)

16

i10Index(all)

18

i10Index(since 2020)

18

Email

University Profile Page

Google Scholar

André Biedenkapp Skills & Research Interests

Dynamic Algorithm Configuration

Learning to Learn

Deep Reinforcement Learning

AutoML

AutoRL

Top articles of André Biedenkapp

Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning

arXiv preprint arXiv:2404.09521

2024/4/15

André Biedenkapp
André Biedenkapp

H-Index: 5

Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization

arXiv preprint arXiv:2403.10967

2024/3/16

Raghu Rajan
Raghu Rajan

H-Index: 2

André Biedenkapp
André Biedenkapp

H-Index: 5

Hierarchical Transformers are Efficient Meta-Reinforcement Learners

arXiv preprint arXiv:2402.06402

2024/2/9

MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning

Journal of Artificial Intelligence Research

2023/7/12

Contextualize Me--The Case for Context in Reinforcement Learning

arXiv preprint arXiv:2202.04500

2022/2/9

Gray-Box Gaussian Processes for Automated Reinforcement Learning

2022/9/29

Automated Dynamic Algorithm Configuration

Journal of Artificial Intelligence Research

2022/12/30

AutoRL-Bench 1.0

2022/10/21

Dynamic Algorithm Configuration by Reinforcement Learning

2022/10/14

André Biedenkapp
André Biedenkapp

H-Index: 5

Training of Machine Learning Systems for Image Processing

2022/7/21

Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration

2022/7/8

Learning Domain-Independent Policies for Open List Selection

2022

DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning

arXiv preprint arXiv:2206.03493

2022/6/7

Method and Device for Learning a Strategy and For Implementing the Strategy

2022/1/27

SMAC3: A versatile Bayesian optimization package for hyperparameter optimization

Journal of Machine Learning Research

2022

Sample-Efficient Automated Deep Reinforcement Learning

2020

André Biedenkapp
André Biedenkapp

H-Index: 5

Frank Hutter
Frank Hutter

H-Index: 52

On the Importance of Hyperparameter Optimization for Model-Based Reinforcement Learning

2021/3/18

In-Loop Meta-Learning with Gradient-Alignment Reward

AAAI Workshop on Meta-Learning Challenges 2021

2021/2/5

Device and Method for Planning an Operation of a Technical System

2021/12/9

See List of Professors in André Biedenkapp University(Albert-Ludwigs-Universität Freiburg)

Co-Authors

academic-engine