A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Policy mirror ascent achieves Nash equilibrium in mean field games without a population generative model.
New algorithm for optimizing statistical utilities in bandits.
MoMA improves model-based RL by using unrestricted policy classes.
A new framework improves reinforcement learning algorithms with policy guarantees.
We present a new algorithm based on an gradient ascent for a general Active Exploration bandit problem in the fixed confidence setting. This problem encompasses several well studied problems such that the Best Arm Identification or Thresholding Bandits. It consists of a new sampling rule based on an online lazy mirror …