AI RESEARCH
Vanishing L2 regularization for the softmax Multi Armed Bandit
arXiv CS.LG
•
ArXi:2605.03752v1 Announce Type: new Multi Armed Bandit (MAB) algorithms are a cornerstone of reinforcement learning and have been studied both theoretically and numerically. One of the most commonly used implementation uses a softmax mapping to prescribe the optimal policy and served as the foundation for downstream algorithms, including REINFORCE. Distinct from vanilla approaches, we consider here the L2 regularized softmax policy gradient where a quadratic term is subtracted from the mean reward.