Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization
Yuan Xue, Daniel Kudenko, Megha Khosla
Structure-based drug design has been accelerated by pocket-aware 3D generative models, yet most methods primarily fit the training distribution and may fall short of satisfying mul…
cs.LG2025
Improving the Effectiveness of Potential-Based Reward Shaping in Reinforcement Learning
Henrik Müller, Daniel Kudenko
Potential-based reward shaping is commonly used to incorporate prior knowledge of how to solve the task into reinforcement learning because it can formally guarantee policy invaria…