Research map / Reinforcement learning / MDPs and planning
Safe Reinforcement Learning in Constrained Markov Decision Processes
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 |
|---|---|---|---|
| Add practical early stopping of safety exploration (pes²) (ablation) | SNO-MDP · Mars surface exploration | Reward: 0.49 -> 0.81 | Helped |
| Add theoretically guaranteed early stopping of safety exploration (es²) (ablation) | SNO-MDP · Mars surface exploration | Reward: 0.49 -> 0.78 | Helped |
| Use SNO-MDP with pes² instead of SafeExpOpt-MDP | Mars surface exploration · Mars surface exploration | Reward: 0.59 -> 0.81 | Helped |
| Use SNO-MDP with es² instead of SafeExpOpt-MDP | Mars surface exploration · Mars surface exploration | Reward: 0.59 -> 0.78 | Helped |
| Use SNO-MDP instead of SafeMDP | Mars surface exploration · Mars surface exploration | Reward: 0.34 -> 0.49 | Helped |
| Use SNO-MDP instead of SafeExpOpt-MDP | Mars surface exploration · Mars surface exploration | Reward: 0.59 -> 0.49 | Hurt |
| Add pes² rather than es² (ablation) | SNO-MDP · Mars surface exploration | Reward: 0.78 -> 0.81 | Helped |
| Use SNO-MDP with pes² instead of SafeMDP | Mars surface exploration · Mars surface exploration | Reward: 0.34 -> 0.81 | Helped |
Closest papers by meaning
- Safe Exploration and Optimization of Constrained MDPs Using Gaussian Processes (AAAI 2018 · similarity 0.94)
- Probabilistic Shielding for Safe Reinforcement Learning (AAAI 2025 · similarity 0.90)
- Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis (AAAI 2024 · similarity 0.90)
- Near-Optimal Sample Complexity for Online Constrained MDPs (NeurIPS 2025 · similarity 0.90)
- Flipping-based Policy for Chance-Constrained Markov Decision Processes (NeurIPS 2024 · similarity 0.89)
- Safety Representations for Safer Policy Learning (ICLR 2025 · 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.