Marco Caccamo

Full Professor, Technische Universität München

Joined

July 2019

Names

Marco Caccamo

Emails

****@cs.uiuc.edu (Confirmed)

****@tum.de (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Full Professor

Technische Universität München (tum.de)

2018 – Present

Full Professor

University of Illinois at Urbana-Champaign (illinois.edu)

2015 – 2018

Advisors, Relations & Conflicts

PhD Advisee

Rodolfo Pellizzoni

Present

PhD Advisee

Renato Mancuso

2013 – Present

Coworker

Tarek F. Abdelzaher

2004 – Present

Coworker

Lui Sha

2002 – Present

Expertise

Real-Time and Embedded Systems

1997 – Present

Publications

AutoSafe: A Safe Neural Policy Network with Safety Common Sense
Hongpeng Cao, Liqun Zhao, Lui Sha, Marco Caccamo
- Submitted to ICLR 2026
- Readers: Everyone
Impoola: The Power of Average Pooling for Image-based Deep Reinforcement Learning
Raphael Trumpp, Ansgar Schäfftlein, Mirco Theile, Marco Caccamo
- RLC 2025
- Readers: Everyone
Action Mapping for Reinforcement Learning in Continuous Environments with Constraints
Mirco Theile, Lukas Dirnberger, Raphael Trumpp, Marco Caccamo, Alberto Sangiovanni-Vincentelli
- RLC 2025
- Readers: Everyone
The Case for Gradual Structured Pruning in Image-based Deep Reinforcement Learning
Raphael Trumpp, Mirco Theile, Marco Caccamo
- Submitted to ICLR 2025
- Readers: Everyone
Action Mapping for Reinforcement Learning in Continuous Environments with Constraints
Mirco Theile, Lukas Dirnberger, Raphael Trumpp, Marco Caccamo, Alberto Sangiovanni-Vincentelli
- Submitted to ICLR 2025
- Readers: Everyone
Runtime Learning Machine
Hongpeng Cao, Yanbing Mao, Yihao Cai, Lui Sha, Marco Caccamo
- Submitted to ICLR 2025
- Readers: Everyone
Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
Hongpeng Cao, Yanbing Mao, Lui Sha, Marco Caccamo
- ICLR 2024 spotlight
- Readers: Everyone
6IMPOSE: Bridging the Reality Gap in 6D Pose Estimation for Robotic Grasping
Hongpeng Cao, Lukas Dirnberger, Daniele Bernardini, Cristina Piazza, Marco Caccamo
- 13 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Learning to Generate All Feasible Actions
Mirco Theile, Daniele Bernardini, Raphael Trumpp, Cristina Piazza, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli
- Published: 01 Jan 2023, Last Modified: 12 May 2023
- CoRR 2023
- Readers: Everyone
Residual Policy Learning for Vehicle Control of Autonomous Racing Cars
Raphael Trumpp, Denis Hoornaert, Marco Caccamo
- Published: 01 Jan 2023, Last Modified: 12 May 2023
- CoRR 2023
- Readers: Everyone

View all 169 publications

Co-Authors

View all 161 co-authors