Tootfinder

Epistemically-guided forward-backward exploration
N\'uria Armengol Urp\'i, Marin Vlastelica, Georg Martius, Stelian Coros
https://arxiv.org/abs/2507.05477

Epistemically-guided forward-backward exploration
Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, FB and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other …

Spain arrests two over data leaks targeting state officials, journalists https://therecord.media/spain-arrests-two-data-leaks-targeting-gov-officials-journalists