Research map / Reinforcement learning / Policy gradient and actor-critic
Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential
Xingang Guo, Bin Hu
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 |
|---|---|---|---|
| Run GS, NS, INGD and model-free NS on the example system | Goldstein-subdifferential policy search · 3-state H-infinity example | relative error trajectory | Improved |
| Replace model-based NS with model-free NS (power-iteration H-infinity estimation) (ablation) | NS method · 3-state H-infinity example | relative error trajectory | No clear effect |
| Run NS on 8 randomly generated systems | NS method · random 3x3 systems | relative optimality gap | Improved |
| Decrease number of samples used in H-infinity estimation (noisier oracle) (ablation) | model-free NS · 3-state H-infinity example | convergence behavior | Hurt |
Closest papers by meaning
- Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control (NeurIPS 2023 · similarity 0.93)
- Time-Constrained Robust MDPs (NeurIPS 2024 · similarity 0.86)
- Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees (NeurIPS 2025 · similarity 0.85)
- Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction (NeurIPS 2026 · similarity 0.85)
- A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes (ICML 2024 · similarity 0.85)
- Convergence of Policy Mirror Descent Beyond Compatible Function Approximation (ICML 2025 · similarity 0.84)
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.
