Research map / Bandits and online learning / RL theory and MDPs
Provably Safe Reinforcement Learning with Step-wise Violation Constraints
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 SUCBVI with step-wise safety constraints instead of unconstrained UCBVI | Safe-RL-SW · Safe-RL-SW experiment | step-wise violation | Helped |
| Use SUCBVI with step-wise safety constraints instead of CMDP algorithms | Safe-RL-SW · Safe-RL-SW experiment | reward under safety constraints | Helped |
| Use SRF-UCRL instead of RF-UCRL for safe reward-free exploration | Safe-RFE-SW · Safe-RFE-SW experiment | expected violation of output policy | Helped |
Closest papers by meaning
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.92)
- Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs (NeurIPS 2021 · similarity 0.91)
- Towards Safe Reinforcement Learning with a Safety Editor Policy (NeurIPS 2022 · similarity 0.91)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.90)
- Safety Representations for Safer Policy Learning (ICLR 2025 · similarity 0.90)
- 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.