Research map / Optimization / Nonconvex and smooth optimization
On the Global Convergence Rates of Softmax Policy Gradient Methods
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Entropy regularization added to softmax policy gradient (maximum entropy reward) | softmax policy gradient in tabular MDPs · general MDPs (theoretical) | convergence rate of suboptimality | Helped |
| Unregularized softmax policy gradient with true gradient (uniform initialization) | softmax policy gradient · bandit case (theoretical) | suboptimality (pi*-pi_theta)^T r upper bound | No clear effect |
| Entropy regularization vs. no regularization on softmax policy gradient lower bound | softmax policy gradient · general MDPs (theoretical lower bound) | suboptimality lower bound | Mixed |
| Entropy regularization added to policy gradient (Łojasiewicz degree analysis) | expected reward objective · bandit case (theoretical) | non-uniform Łojasiewicz degree | Helped |
Closest papers by meaning
- Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with $\boldsymbol{f}$-SoftArgmax Parameterization $\&$ Coupled Regularization (ICLR 2026 · similarity 0.95)
- Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs (NeurIPS 2026 · similarity 0.93)
- Convergence of Policy Mirror Descent Beyond Compatible Function Approximation (ICML 2025 · similarity 0.88)
- Policy Gradient with Tree Expansion (ICML 2025 · similarity 0.88)
- Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods (ICLR 2024 · similarity 0.88)
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.