Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits

arXiv:2505.03155 · cs.LG · Submitted 2025-05-06 · Read on arXiv

cs.LG

Submitted: 2025-05-06

Updated: 2026-10-01

Comments: 88 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Action Space — 1× in this paper · explained in 1 episode
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Exploration-Enhanced POLITEX
• Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization
• Fast Convergence of Stochastic Gradient Descent under a Strong Growth Condition
• Proximal Policy Optimization Algorithms

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks