Research map / Reinforcement learning / Policy gradient and actor-critic
Safe Reinforcement Learning by Imagining the Near Future
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 |
|---|---|---|---|
| increase terminal safety cost C (ablation) | SMBPO · MuJoCo safety tasks | safety violations vs reward | Mixed |
| rollout horizon H=10 instead of H=5 (ablation) | SMBPO · MuJoCo safety tasks | return | Helped |
| add safety-violation penalty (SMBPO vs MBPO with C=0) | MBPO · MuJoCo safety tasks | cumulative safety violations | Helped |
| use average over ensemble models for TD target instead of min (ablation) | SMBPO · MuJoCo safety tasks | performance | Helped |
Closest papers by meaning
- Safety Representations for Safer Policy Learning (ICLR 2025 · similarity 0.91)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.90)
- Probabilistic Shielding for Safe Reinforcement Learning (AAAI 2025 · similarity 0.90)
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 2024 · similarity 0.90)
- Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis (AAAI 2024 · similarity 0.90)
- SafeDreamer: Safe Reinforcement Learning with World Models (ICLR 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.