Daniel Palenicek

@daniel-palenicek.bsky.social

PhD Researcher in Robot #ReinforcementLearning 🤖🧠 at IAS TU Darmstadt and hessian.AI advised by Jan Peters. Former intern at BCAI and Huawei R&D UK.

Headed to Rio for #ICLR 🇧🇷 come say hi at our poster! XQC: a principled look at critic optimization. BN+WN+cross-entropy → condition numbers orders of magnitude smaller than baselines. SOTA on 70 continuous ctrl tasks w/ 4.5× less params. 📅 Thu, 1030–1300 📍 Pavilion 4, #4518

Daniel Palenicek@daniel-palenicek.bsky.social · 12mo ago

🚀 New preprint! Introducing XQC— a simple, well-conditioned actor-critic that achieves SOTA sample efficiency in #RL ✅ ~4.5× fewer parameters than SimbaV2 ✅ Scales to vision-based RL 👉 arxiv.org/pdf/2509.25174 Thanks to Florian Vogt @joemwatson.bsky.social @jan-peters.bsky.social

🎉 Really excited, our paper "XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning" has been accepted at #ICLR2026. If you are interested in reinforcement learning, sample-efficiency, compute-efficiency go check it out. See you in Rio!

Daniel Palenicek@daniel-palenicek.bsky.social · 12mo ago

🚀 New preprint! Introducing XQC— a simple, well-conditioned actor-critic that achieves SOTA sample efficiency in #RL ✅ ~4.5× fewer parameters than SimbaV2 ✅ Scales to vision-based RL 👉 arxiv.org/pdf/2509.25174 Thanks to Florian Vogt @joemwatson.bsky.social @jan-peters.bsky.social