Author name: Ian Osband

arXiv:2605.13287v1 Announce Type: cross
Abstract: Most exploration algorithms search broadly until uncertainty is resolved. When the action space is too large to resolve within budget, practitioners default to $\varepsilon$-greedy, which bounds disrup…

arXiv:2603.20521v2 Announce Type: replace-cross
Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log-probability) under the learner’s policy. The core …