2 papers
cs.LG2026
Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift
Robin Holzinger, Riccardo Colletti
Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems. However, t…
cs.LG2026
KLip-PPO: A per-sample KL perspective on PPO-Clip
Riccardo Colletti, Robin Holzinger
Proximal Policy Optimization (PPO) is the standard policy-gradient algorithm for on-policy reinforcement learning. The literature presents it in two forms, a clipped surrogate that…