影响力指数

44.96/100

前 11%

全站排名 #7,070

发表论文3 篇

平均评分7.0

年均产出3.0 篇/年

Tal Lancewicki

Researcher@Meta·美国·OpenReview

研究方向

Online learning · Reinforcement learning · Multi-armed bandit

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback

NeurIPS 2025Poster

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback

ICML 2025Poster

Individual Regret in Cooperative Stochastic Multi-Armed Bandits

NeurIPS 2025Poster

合作者 (4)

博士导师3 篇

Ofir Schlisselberg