Research map / Reinforcement learning / Policy gradient and actor-critic
On the Stability and Convergence of Robust Adversarial Reinforcement Learning: A Case Study on Linear Quadratic Systems
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 |
|---|---|---|---|
| initialize with a merely stabilizing controller K0=-4.6 (not robustly stabilizing) instead of robustly stabilizing K0 | conventional alternating RARL · 1-D LQ example 3.2 | stability of iterates | Hurt |
| start from robustly stabilizing K0=-6.6 with large NK=NL=100 best-response updates | alternating RARL · 1-D LQ example 3.6 | stability of iterates | Hurt |
| use double-loop NPG (inner loop solves L exactly, one outer K step) with robustly stabilizing K0 | LQ RARL · LQ game | convergence to Nash equilibrium | Helped |
| use NL=1 or simultaneous descent-ascent updates with robustly stabilizing initialization (ablation) | LQ RARL · LQ simulations | convergence to Nash equilibrium | Mixed |
| robustify initialization by H-infinity norm subgradient descent until norm < 1 (ablation) | LQ RARL descent-ascent · 1-D LQ example 5.4 | convergence to Nash equilibrium | Helped |
Closest papers by meaning
- Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula (ICLR 2024 · similarity 0.91)
- Adversarial Diffusion for Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach (NeurIPS 2024 · similarity 0.89)
- Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies (ICLR 2024 · similarity 0.89)
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient (NeurIPS 2025 · similarity 0.89)
- Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error (ICML 2024 · similarity 0.88)
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.