Research map / Optimization / Nonconvex and smooth optimization
Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
Dongsheng Ding, Chen-Yu Wei, Kaiqing Zhang, Alejandro Ribeiro
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add entropy regularization to primal-dual policy gradient (RPG-PD) | NPG-PD · constrained MDP computational experiment | oscillation and constraint satisfaction | Improved |
| add optimism to primal-dual policy gradient (OPG-PD) | NPG-PD · constrained MDP computational experiment | oscillation and constraint satisfaction | Improved |
| regularization in RPG-PD relative to OPG-PD | RPG-PD · constrained MDP computational experiment | reward | Hurt |
| use PID Lagrangian instead of OPG-PD | PID Lagrangian · constrained MDP computational experiment | reward | Hurt |
| increase constant stepsize of OPG-PD up to 0.2 (ablation) | OPG-PD · constrained MDP computational experiment | convergence rate | Improved |
Closest papers by meaning
- Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs (AAAI 2025 · similarity 0.94)
- Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs (NeurIPS 2026 · similarity 0.93)
- Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm (NeurIPS 2025 · similarity 0.91)
- Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm (NeurIPS 2024 · similarity 0.91)
- Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Accelerated Policy Gradient for s-rectangular Robust MDPs with Large State Spaces (ICML 2024 · similarity 0.89)
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.
