Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness
Chenyu Gan
We study cooperative multiplayer bandits with adversarial rewards and no collision information. In each of rounds, each of labeled players picks one of arms. A player…
cs.LG2026
Rising Multi-Armed Bandits with Known Horizons
Seockbean Song, Chenyu Gan, Youngsik Yoon +3
Rising Multi-Armed Bandits (RMABs) model sequential decision problems where each arm's expected reward improves with repeated pulls. In such problems, the value of investing in an…