Research map / Reinforcement learning / MDPs and planning
A Lyapunov-based Approach to Safe Reinforcement Learning
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 |
|---|---|---|---|
| Use Lyapunov-induced local policy constraints instead of the unconstrained policy update | SPI and SVI · 2D grid-world CMDP planning | constraint satisfaction | Helped |
| Use SPI rather than the surrogate CMDP algorithms | 2D grid-world CMDP planning · 2D grid-world CMDP planning across obstacle densities | return | Helped |
| Use SVI as obstacle density grows | SVI · 2D grid-world CMDP planning | return | Hurt |
| Use the Lagrangian method instead of a Lyapunov-based safe DP method | 2D grid-world CMDP planning · 2D grid-world CMDP planning at higher obstacle density | constraint satisfaction | Hurt |
| Use SDPI or SDQN instead of unconstrained DPI or DQN | Safe RL algorithms · 2D grid-world safe RL tasks | constraint satisfaction | Helped |
| Use SDPI or SDQN instead of the Lagrangian safe RL approach | Safe RL algorithms · 2D grid-world safe RL tasks | constraint satisfaction | Helped |
| Use the Lagrangian safe RL approach instead of SDPI or SDQN | Safe RL algorithms · 2D grid-world safe RL tasks | return | Hurt |
Closest papers by meaning
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 2024 · similarity 0.92)
- Probabilistic Shielding for Safe Reinforcement Learning (AAAI 2025 · similarity 0.91)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.91)
- Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis (AAAI 2024 · similarity 0.90)
- Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction (NeurIPS 2026 · similarity 0.90)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.90)
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.