Research map / Reinforcement learning / Policy gradient and actor-critic
Safe Policy Optimization with Local Generalized Linear Function Approximations
Akifumi Wachi, Yunyue Wei, Yanan Sui
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 |
|---|---|---|---|
| Use SPO-LF with local features and safety-constrained policy optimization | Gym-MiniGrid 25×25 · Gym-MiniGrid 25×25 | unsafe actions: 0.0 vs 3.4 for Unsafe GLM and 49.0 for Random | Improved |
| Use SPO-LF with local features and safety-constrained policy optimization | Safety-Gym · Safety-Gym | unsafe actions: 0 | Improved |
| Add far-sighted observations by increasing field of view (ablation) | SPO-LF · Gym-MiniGrid | convergence speed | Improved |
| Remove event-triggered safe expansion (ETSE) (ablation) | SPO-LF · Gym-MiniGrid | reward | Hurt |
| Use SPO-LF instead of CPO, PPO-Lagrangian, or TRPO-Lagrangian | Safety-Gym · Safety-Gym | reward | No clear effect |
Closest papers by meaning
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.91)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.91)
- Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation (NeurIPS 2024 · similarity 0.90)
- A Provable Approach for End-to-End Safe Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Safety Representations for Safer Policy Learning (ICLR 2025 · similarity 0.89)
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 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.
