Marius-Constantin Dinu

发表

A Two Time-Scale Update Rule Ensuring Convergence of Episodic Reinforcement Learning Algorithms at the Example of RUDDER

Jose A. Arjona-Medina, S. Hochreiter, Markus Holzleitner, 2022 .

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

Jose A. Arjona-Medina, Vihang P. Patil, S. Hochreiter, 2020, ICML.

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2022, CoLLAs.

R EACTIVE E XPLORATION TO C OPE WITH N ON -S TATIONARITY IN L IFELONG R EINFORCEMENT L EARNING

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2022 .

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2022, CoLLAs.

A Dataset Perspective on Offline Reinforcement Learning

Vihang P. Patil, S. Hochreiter, Hamid Eghbal-zadeh, 2021, CoLLAs.

The balancing principle for parameter choice in distance-regularized domain adaptation

Bernhard Nessler, Hamid Eghbal-zadeh, W. Zellinger, 2021, NeurIPS.

Understanding the Effects of Dataset Characteristics on Offline Reinforcement Learning pdf

Sepp Hochreiter, Markus Hofmarcher, Philipp Renz, 2021, ArXiv.

InfODist: Online distillation with Informative rewards improves generalization in Curriculum Learning

S. Hochreiter, Markus Holzleitner, Michael Kopp, 2022 .

XAI and Strategy Extraction via Reward Redistribution

Jose A. Arjona-Medina, S. Hochreiter, Johannes Brandstetter, 2020, xxAI@ICML.

SymbolicAI: A framework for logic-based approaches combining generative models and solvers

Markus Holzleitner, Marius-Constantin Dinu, Sepp Hochreiter, 2024, ArXiv.