Research map / Reinforcement learning / Policy gradient and actor-critic
WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained 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 a lower risk level, α=0.1 rather than α=0.9 (ablation) | WCSAC · StaticEnv | cost-CVaR-0.1: 31.4 -> 14.3 | Helped |
| Use a lower risk level, α=0.1 rather than α=0.9 (ablation) | WCSAC · StaticEnv | expected return: 0.56 -> -0.43 | Hurt |
Closest papers by meaning
- Safe Multi-Agent Reinforcement Learning via Distributional Safety Critic and Maximum Entropy Optimization (AAAI 2026 · similarity 0.91)
- Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation (AAAI 2024 · similarity 0.88)
- Safety Representations for Safer Policy Learning (ICLR 2025 · similarity 0.88)
- Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 2024 · similarity 0.87)
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.