Pre‑trained vision models boost robustness of model‑based RL under severe visual domain shifts; partial fine‑tuning of higher layers gives the best performance. Read more: https://getnews.me/pre-trained-vision-models-improve-generalization-in-model-based-rl/ #pretrainedvision #modelbasedrl

This was an amazing collaboration with a cracked team consisting of @cvoelcker.bsky.social, me, Arash Ahmadian, Romina Abachi, @igilitschenski.bsky.social, and @sologen.bsky.social

#ReinforcementLearning #ModelBasedRL #RLTheory #ICML2025

PO‑MPC adds a KL‑divergence term to align policies with MPPI planners, weighting the KL to boost sample efficiency and stabilize learning on continuous‑control benchmarks. Read more: https://getnews.me/kl-regularization-boosts-adaptive-planning-in-model-based-rl/ #modelbasedrl #klregularization