1 citations · 1 across the 4 of their papers we have counts for
5 papers
Kolibri: A Sovereign European Model on the Pareto Frontier
Aleph Alpha, :, Moritz Althaus +65
This report introduces Kolibri, an English-German mixture-of-experts transformer with 78.1B total parameters and 3.46B active parameters per token, released as open weights under t…
Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching
Serge Thilges, Onur Celik, Denis Blessing +2
Diffusion policies have recently emerged as a powerful paradigm for representing complex action distributions in reinforcement learning (RL). However, their application to online R…
PAWS: Preference Learning with Advantage-Weighted Segments
Aleksandar Taranovic, Onur Celik, Niklas Freymuth +6
Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods…
TROLL: Trust Regions improve Reinforcement Learning for Large Language Models
Philipp Becker, Niklas Freymuth, Serge Thilges +2
Reinforcement Learning (RL) with PPO-like clip objectives has become the standard choice for reward-based fine-tuning of large language models (LLMs). Although recent work has expl…
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
Ge Li, Hongyi Zhou, Dominik Roth +4
Current advancements in reinforcement learning (RL) have predominantly focused on learning step-based policies that generate actions for each perceived state. While these methods e…