Research map / Reinforcement learning / Policy gradient and actor-critic
Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control
Xingang Guo, Darioush Keivan, Geir Dullerud, Peter Seiler, 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 |
|---|---|---|---|
| model-free zeroth-order method vs model-based HIFOO on AC15 | Algorithm 1 · COMPleib AC15 | H-infinity norm: 15.2919 -> 15.4141 | No clear effect |
| model-free method vs HIFOO on HF2D11 | Algorithm 1 · COMPleib HF2D11 | H-infinity norm: 7.7237 × 104 -> 7.7223 × 104 | No clear effect |
| model-free method vs HIFOO on DLR2 | Algorithm 1 · COMPleib DLR2 | H-infinity norm: 4.0066 × 103 -> 4.0094 × 103 | No clear effect |
| model-free method vs HIFOO on HE4 | Algorithm 1 · COMPleib HE4 | H-infinity norm: 22.8382 -> 22.8538 | No clear effect |
| inexact instead of exact zeroth-order oracle | Algorithm 1 · random systems | relative error | No clear effect |
| larger system dimension nx = 10, 50, 100 | Algorithm 1 · random systems | relative error | No clear effect |
| decrease target epsilon | Algorithm 1 · random systems | oracle calls | Hurt |
Closest papers by meaning
- Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential (NeurIPS 2022 · similarity 0.93)
- Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity (NeurIPS 2021 · similarity 0.88)
- Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems (JMLR 2020 · similarity 0.88)
- Truly Deterministic Policy Optimization (NeurIPS 2022 · similarity 0.87)
- Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees (NeurIPS 2025 · similarity 0.86)
- Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs (AAAI 2025 · similarity 0.85)
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.
