Softmax gradient policy for variance minimization and risk-averse multi armed bandits

The paper introduces a new algorithm for the Multi‑Armed Bandit problem that prioritizes selecting the arm with the lowest variance rather than the highest expected reward, using a softmax policy parameterization. It constructs an unbiased estimate of the minimal‑variance objective by drawing two independent samples from the chosen arm and proves convergence under natural conditions. Numerical experiments demonstrate the algorithm’s practical behavior and provide implementation guidance, while also addressing general risk‑aware trade‑offs between average reward and variance.

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.

• reinforcement-learning