Varun Raj Kompella

Senior Research Scientist, Sony AI

Joined

July 2019

Names

Varun Raj Kompella (Preferred)

Emails

****@sony.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Senior Research Scientist

Sony AI (sony.com)

2019 – Present

PhD student

IDSIA / Universita della Svizzera Italiana (usi.ch)

2010 – 2014

MS student

INRIA / Institut polytechnique de Grenoble (inpg.fr)

2008 – 2009

Advisors, Relations & Conflicts

Postdoc Advisor

Laurenz Wiskott

2015 – 2017

PhD Advisor

Juergen Schmidhuber

2010 – 2014

Expertise

Slow feature analysis

Present

Reinforcement Learning Theory and Applications

Present

Publications

Outracing champion Gran Turismo drivers with deep reinforcement learning
Peter R. Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani H. Gilpin, Piyush Khandelwal, Varun Raj Kompella, HaoChih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D Thomure, Houmehr Aghabozorgi et al. (7 additional authors not shown)
- 09 May 2023 (modified: 09 May 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
Event Tables for Efficient Experience Replay
Varun Raj Kompella, Thomas Walsh, Samuel Barrett, Peter R. Wurman, Peter Stone
- Accepted by TMLR
- Readers: Everyone
Utilizing Slow Feature Analysis for Lipreading
Jan Freiwald, Mahdie Karbasi, Steffen Zeiler, Jan Melchior, Varun Raj Kompella, Laurenz Wiskott, Dorothea Kolossa
- 2018 (modified: 16 May 2022)
- ITG Symposium on Speech Communication 2018
- Readers: Everyone
Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots
Varun Raj Kompella, Marijn F. Stollenga, Matthew D. Luciw, Jürgen Schmidhuber
- 2017 (modified: 16 May 2022)
- Artif. Intell. 2017
- Readers: Everyone
Intrinsically Motivated Acquisition of Modular Slow Features for Humanoids in Continuous and Non-Stationary Environments
Varun Raj Kompella, Laurenz Wiskott
- 2017 (modified: 16 May 2022)
- CoRR 2017
- Readers: Everyone
Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis
Varun Raj Kompella, Matthew D. Luciw, Marijn F. Stollenga, Jürgen Schmidhuber
- 2016 (modified: 16 May 2022)
- Neural Comput. 2016
- Readers: Everyone
Explore to see, learn to perceive, get the actions for free: SKILLABILITY
Varun Raj Kompella, Marijn F. Stollenga, Matthew D. Luciw, Jürgen Schmidhuber
- 2014 (modified: 16 May 2022)
- IJCNN 2014
- Readers: Everyone
An Anti-hebbian Learning Rule to Represent Drive Motivations for Reinforcement Learning
Varun Raj Kompella, Sohrob Kazerounian, Jürgen Schmidhuber
- 2014 (modified: 16 May 2022)
- SAB 2014
- Readers: Everyone
An intrinsic value system for developing multiple invariant representations with incremental slowness learning
Matthew D. Luciw, Varun Raj Kompella, Sohrob Kazerounian, Jürgen Schmidhuber
- 2013 (modified: 16 May 2022)
- Frontiers Neurorobotics 2013
- Readers: Everyone
Autonomous learning of abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis
Varun Raj Kompella, Matthew D. Luciw, Marijn F. Stollenga, Leo Pape, Jürgen Schmidhuber
- 2012 (modified: 16 May 2022)
- ICDL-EPIROB 2012
- Readers: Everyone

View all 16 publications

Co-Authors

View all 40 co-authors