Követés
Marius-Constantin Dinu
Marius-Constantin Dinu
PhD, Institute of Machine Learning, JKU, Linz, ExtensityAI Research Scientist
E-mail megerősítve itt: ml.jku.at - Kezdőlap
Cím
Hivatkozott rá
Hivatkozott rá
Év
Align-rudder: Learning from few demonstrations by reward redistribution
VP Patil, M Hofmarcher, MC Dinu, M Dorfer, PM Blies, J Brandstetter, ...
arXiv preprint arXiv:2009.14108, 2020
602020
A Dataset Perspective on Offline Reinforcement Learning
K Schweighofer, A Radler, MC Dinu, M Hofmarcher, V Patil, ...
arXiv preprint arXiv:2111.04714, 2021
532021
Large Language Models Can Self-Improve At Web Agent Tasks
A Patel, M Hofmarcher, C Leoveanu-Condrei, MC Dinu, C Callison-Burch, ...
arXiv preprint arXiv:2405.20309, 2024
172024
Addressing parameter choice issues in unsupervised domain adaptation by aggregation
MC Dinu, M Holzleitner, M Beck, HD Nguyen, A Huber, H Eghbal-zadeh, ...
arXiv preprint arXiv:2305.01281, 2023
172023
Reactive exploration to cope with non-stationarity in lifelong reinforcement learning
CA Steinparz, T Schmied, F Paischer, MC Dinu, VP Patil, A Bitto-Nemling, ...
Conference on Lifelong Learning Agents, 441-469, 2022
172022
The balancing principle for parameter choice in distance-regularized domain adaptation
W Zellinger, N Shepeleva, MC Dinu, H Eghbal-zadeh, HD Nguyen, ...
Advances in Neural Information Processing Systems 34, 20798-20811, 2021
152021
SymbolicAI: A framework for logic-based approaches combining generative models and solvers
MC Dinu, C Leoveanu-Condrei, M Holzleitner, W Zellinger, S Hochreiter
arXiv preprint arXiv:2402.00854, 2024
112024
XAI and strategy extraction via reward redistribution
MC Dinu, M Hofmarcher, VP Patil, M Dorfer, PM Blies, J Brandstetter, ...
International Workshop on Extending Explainable AI Beyond Deep Models and …, 2020
112020
InfODist: Online distillation with Informative rewards improves generalization in Curriculum Learning
R Siripurapu, VP Patil, K Schweighofer, MC Dinu, T Schmied, LEF Diez, ...
Deep Reinforcement Learning Workshop NeurIPS 2022, 2022
32022
Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning
MC Dinu
Johannes Kepler University, PhD Thesis, 2024
2024
SymbolicAI: A Neuro-Symbolic Perspective on Large Language Models (LLMs)
MC Dinu
https://github.com/Xpitfire/symbolicai, 2022
2022
Ensemble Learning for Domain Adaptation by Importance Weighted Least Squares
MC Dinu, M Holzleitner, M Beck, DH Nguyen, A Huber, H Eghbal-zadeh, ...
2022
Overcoming Catastrophic Forgetting with Context-Dependent Activations
MC Dinu
2019
A Two Time-Scale Update Rule Ensuring Convergence of Episodic Reinforcement Learning Algorithms at the Example of RUDDER
MHJA Arjona-Medina, MC Dinu, AVLGS Hochreiter
2019
Endbericht zum Berufspraktikum
MC Dinu
2016
Cross-Language Compiler using Roslyn and Coco/R for the Common Language Runtime
MC Dinu
2016
Supplementary material for: The balancing principle for parameter choice in distance-regularized domain adaptation
W Zellinger, N Shepeleva, MC Dinu, H Eghbal-zadeh, DH Nguyen, ...
A rendszer jelenleg nem tudja elvégezni a műveletet. Próbálkozzon újra később.
Cikkek 1–17