banner
davidleeftink.bsky.social
David Leeftink
@davidleeftink.bsky.social
28 followers 98 following 4 posts
PhD student in Machine learning @ Donders Institute Nijmegen | Probabilistic Machine Learning, Control, Reinforcement Learning.
Posts Media Videos Starter Packs
Pinned
davidleeftink.bsky.social
David Leeftink @davidleeftink.bsky.social · Sep 3
Our recent paper “Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimization,” has been accepted to CDC 2025!

We demonstrate how applying optimal control principles can significantly improve planning in deep model-based reinforcement learning with epistemic uncertainty.
1 1 7
davidleeftink.bsky.social
David Leeftink @davidleeftink.bsky.social · 5d
I'd say yes! It allows new ideas to distribute faster, while remaining clear that it is not a reviewed article
1
davidleeftink.bsky.social
David Leeftink @davidleeftink.bsky.social · Sep 4
I'd like to!
1 1
davidleeftink.bsky.social
David Leeftink @davidleeftink.bsky.social · Sep 3
📄 Read the full paper: arxiv.org/abs/2504.02543
💻 Code available on GitHub: github.com/DavidLeeftin...

A huge thank you to everyone who contributed to this work!

#CDC2025 #ReinforcementLearning #OptimalControl #MachineLearning
Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimization
Without exact knowledge of the true system dynamics, optimal control of non-linear continuous-time systems requires careful treatment under epistemic uncertainty. In this work, we translate a probabil...
arxiv.org
1
davidleeftink.bsky.social
David Leeftink @davidleeftink.bsky.social · Sep 3
Our recent paper “Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimization,” has been accepted to CDC 2025!

We demonstrate how applying optimal control principles can significantly improve planning in deep model-based reinforcement learning with epistemic uncertainty.
1 1 7