Research map / Reinforcement learning / Policy gradient and actor-critic
Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
Yuping Luo, Tengyu Ma
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 |
|---|---|---|---|
| co-train barrier certificates, the dynamics model, and the policy, and explore only within certified states | CRABS · Upright, Tilt, Move, and Swing | safety violations | Improved |
| learn the barrier certificate rather than use a handcrafted certificate (ablation) | CRABS · designed tasks | total reward | Improved |
| learn the barrier certificate rather than use a handcrafted certificate (ablation) | CRABS · designed tasks | safety violations | Improved |
| add regularization encouraging the certified region to include the previous epoch's region (ablation) | CRABS barrier certificate · Move | size of certified viable subset | Improved |
| use SAC instead of CRABS | CRABS · Move and Swing | total reward | Hurt |
Closest papers by meaning
- A Provable Approach for End-to-End Safe Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- P2BPO: Permeable Penalty Barrier-Based Policy Optimization for Safe RL (AAAI 2024 · similarity 0.89)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.89)
- Boundary-to-Region Supervision for Offline Safe Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Offline Safe Reinforcement Learning Using Trajectory Classification (AAAI 2025 · similarity 0.89)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · 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.
