作者位次 #2/4ICLR 2026Poster· Theory / Reinforcement Learning and Planning
Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with $\boldsymbol{f}$-SoftArgmax Parameterization $\&$ Coupled Regularization
Safwan Labbi · Daniil Tiapkin · Paul Mangold · Eric Moulines