Research map / Reinforcement learning / Offline RL
Offline Reinforcement Learning with Differential Privacy
Dan Qiao, Yu-Xiang Wang
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 differential privacy (Gaussian noise on counts) to VAPVI | DP-VAPVI · synthetic linear MDP (H=20) | suboptimality / performance | Hurt |
| increase dataset size | DP-VAPVI · synthetic linear MDP (H=20) | performance gap to VAPVI | Improved |
| increase privacy budget (less noise) | DP-VAPVI · synthetic linear MDP (H=20) | performance | Improved |
| use privatized variance-aware LSVI instead of LSVI (DP-VAPVI vs PEVI) | DP-VAPVI · synthetic linear MDP (H=20) | performance | Improved |
Closest papers by meaning
- Differentially Private Reinforcement Learning with Self-Play (NeurIPS 2024 · similarity 0.90)
- On the Sample Complexity of Differentially Private Policy Optimization (NeurIPS 2025 · similarity 0.89)
- Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Towards Differentially Private Reinforcement Learning with General Function Approximation (NeurIPS 2026 · similarity 0.88)
- Online Optimization for Offline Safe Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO (ICML 2025 · similarity 0.86)
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.
