Leif Döring

According to our database, Leif Döring authored at least 10 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

The Role of Target Update Frequencies in Q-Learning.

Simon Weissmann, Tilman Aach, Benedikt Wille, Sebastian Kassing, Leif Döring

CoRR, February, 2026

An Approximate Ascent Approach To Prove Convergence of PPO.

Leif Döring, Daniel Schmidt, Moritz Melcher, Sebastian Kassing, Benedikt Wille, Tilman Aach, Simon Weissmann

CoRR, February, 2026

2025

Clustered KL-barycenter design for policy evaluation.

Simon Weissmann, Till Freihaut, Claire Vernade, Giorgia Ramponi, Leif Döring

CoRR, March, 2025

Almost Sure Convergence of Stochastic Gradient Methods under Gradient Domination.

Simon Weissmann, Sara Klein, Waïss Azizian, Leif Döring

Trans. Mach. Learn. Res., 2025

ADDQ: Adaptive distributional double Q-learning.

Leif Döring, Benedikt Wille, Maximilian Birr, Mihail Bîrsan, Martin Slowik

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Structure Matters: Dynamic Policy Gradient.

Sara Klein, Xiangyuan Zhang, Tamer Basar, Simon Weissmann, Leif Döring

CoRR, 2024

Gradient Span Algorithms Make Predictable Progress in High Dimension.

Felix Benning, Leif Döring

CoRR, 2024

Almost sure convergence rates of stochastic gradient methods under gradient domination.

Simon Weissmann, Sara Klein, Waïss Azizian, Leif Döring

CoRR, 2024

Random Function Descent.

Felix Benning, Leif Döring

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods.

Sara Klein, Simon Weissmann, Leif Döring

Proceedings of the Twelfth International Conference on Learning Representations, 2024