Marius-Constantin Dinu

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 12

Top Topics

Fundamental Issues

Active Exploration

Reactive Agents

Reinforcement Learning

Top Venues

Publications

Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei, Marius-Constantin Dinu, Chris Callison-Burch, Sepp Hochreiter
Large Language Models Can Self-Improve At Web Agent Tasks. CoRR (2024)
Marius-Constantin Dinu, Claudiu Leoveanu-Condrei, Markus Holzleitner, Werner Zellinger, Sepp Hochreiter
SymbolicAI: A framework for logic-based approaches combining generative models and solvers. CoRR (2024)
Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard Alois Moser, Sergei V. Pereverzyev, Sepp Hochreiter, Werner Zellinger
Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation. CoRR (2023)
Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Duc Nguyen, Andrea Huber, Hamid Eghbal-zadeh, Bernhard Alois Moser, Sergei V. Pereverzyev, Sepp Hochreiter, Werner Zellinger
Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation. ICLR (2023)
Christian Alexander Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu, Vihang P. Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter
Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning. CoRR (2022)
Kajetan Schweighofer, Marius-Constantin Dinu, Andreas Radler, Markus Hofmarcher, Vihang Prakash Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter
A Dataset Perspective on Offline Reinforcement Learning. CoLLAs (2022)
Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu, Matthias Dorfer, Patrick M. Blies, Johannes Brandstetter, José Antonio Arjona-Medina, Sepp Hochreiter
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution. ICML (2022)
Christian Alexander Steinparz, Thomas Schmied, Fabian Paischer, Marius-Constantin Dinu, Vihang Prakash Patil, Angela Bitto-Nemling, Hamid Eghbal-zadeh, Sepp Hochreiter
Reactive Exploration to Cope With Non-Stationarity in Lifelong Reinforcement Learning. CoLLAs (2022)
Werner Zellinger, Natalia Shepeleva, Marius-Constantin Dinu, Hamid Eghbal-zadeh, Hoan Duc Nguyen, Bernhard Nessler, Sergei V. Pereverzyev, Bernhard Alois Moser
The balancing principle for parameter choice in distance-regularized domain adaptation. NeurIPS (2021)
Kajetan Schweighofer, Markus Hofmarcher, Marius-Constantin Dinu, Philipp Renz, Angela Bitto-Nemling, Vihang P. Patil, Sepp Hochreiter
Understanding the Effects of Dataset Characteristics on Offline Reinforcement Learning. CoRR (2021)
Marius-Constantin Dinu, Markus Hofmarcher, Vihang P. Patil, Matthias Dorfer, Patrick M. Blies, Johannes Brandstetter, Jose A. Arjona-Medina, Sepp Hochreiter
XAI and Strategy Extraction via Reward Redistribution. xxAI@ICML (2020)
Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu, Matthias Dorfer, Patrick M. Blies, Johannes Brandstetter, Jose A. Arjona-Medina, Sepp Hochreiter
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution. CoRR (2020)