← Back to all news
arXiv AI By Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen

Flickering Multi-Armed Bandits

Read the original on arXiv AI →

arXiv:2602. 17315v3 Announce Type: replace-cross Abstract: We introduce Flickering Multi-Armed Bandits (FMAB) to model sequential decision-making in environments with changing action availability, where accessibility of the next action is restricted to a subset dependent on the agent's current choice.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jun 30

Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting

arXiv:2409. 05980v2 Announce Type: replace-cross Abstract: Rested and Restless Bandits are two well-known bandit settings that are useful to model real-world sequential decision-making problems in which the expected reward of an arm evolves over time due to the actions we perform or due to the nature.

By Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli
reinforcement-learning
More like this →
arXiv Machine Learning
Sep 10

Mixing Makes Markovian Contexts Cheap for Linear Bandits

The paper extends the idea that contexts are cheap for linear bandits from i.i.d. settings to Markovian context processes. By assuming uniform geometric ergodicity, the authors construct a stationary surrogate action set and use a delayed‑update scheme to mitigate bias from nonstationary conditional context distributions. They provide a phased algorithm for unknown stationary distributions and achieve high‑probability regret bounds comparable to standard linear bandit oracles in fast‑mixing regimes, with empirical validation showing gains over LinUCB.

By Kaan Buyukkalayci, Osama Hanna, Christina Fragouli
reinforcement-learningsafety
More like this →