Research map / Reinforcement learning / Policy gradient and actor-critic
Enhancing Safe Exploration Using Safety State Augmentation
Aivar Sootla, Alexander Imani Cowen-Rivers, Jun Wang, Haitham Bou Ammar
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 |
|---|---|---|---|
| Add safety state augmentation to L-PPO (ablation) | L-PPO · Safe pendulum swing-up | constraint violations / convergence | Improved |
| Add safety state augmentation to PID-Lagrangian (ablation) | PID-Lagrangian · Static point goal, safety budgets d=1,10,20 | return and safety cost stability | Improved |
| Add safety budget scheduling (simmering) to PID-L without state augmentation (ablation) | PID-L · Static point goal | training stability | Improved |
| Combine state augmentation with simmering (ablation) | PID-L · Static point goal | return and safety | Improved |
| Simmer PID-L versus PID-L | PID-L · Safety Gym Point and Car tasks | return | No clear effect |
| Simmer PID-L versus PID-L | PID-L · Safety Gym Point and Car tasks | safety cost and cost rate | Improved |
| Use PI-Simmer or Q-Simmer instead of PO-PPO alone | PO-PPO · Probability-one constraints, trajectories with violations | number of violating trajectories | Improved |
| Use PI Simmer rather than Q Simmer | Simmer RL · Probability-one constraints | violations | Improved |
| Apply PI/Q Simmer to average-constrained RL with state augmentation | L-PPO w SA · Pendulum, static point goal | violations | No clear effect |
Closest papers by meaning
- Towards Safe Reinforcement Learning with a Safety Editor Policy (NeurIPS 2022 · similarity 0.94)
- Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms (NeurIPS 2023 · similarity 0.93)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.92)
- Safety Representations for Safer Policy Learning (ICLR 2025 · similarity 0.92)
- Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation (AAAI 2024 · similarity 0.91)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.91)
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.
