Research map / Federated learning and privacy / Differential privacy
Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces
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 the functional-noise level | Privacy-preserving Q-learning · Small example MDP | return | Hurt |
| Reset the Gaussian-process noise every round (J=T/B) | Privacy-preserving Q-learning · Small example MDP | return | Helped |
| Use input perturbation instead of functional noise | Q-learning · Small example MDP | return | Hurt |
| Use the differentially private deep learning framework instead of functional noise | Q-learning · Small example MDP | return | Hurt |
| Use input perturbation or differentially private deep learning at ε=0.45 | Q-learning · Small example MDP, ε=0.45 | return | Hurt |
| Use the policy evaluation method of Balle, Gomrokchi, and Precup | Q-learning · Small example MDP | return | No clear effect |
Closest papers by meaning
- Private Reinforcement Learning with PAC and Regret Guarantees (ICML 2020 · similarity 0.91)
- On the Sample Complexity of Differentially Private Policy Optimization (NeurIPS 2025 · similarity 0.89)
- Towards Differentially Private Reinforcement Learning with General Function Approximation (NeurIPS 2026 · similarity 0.89)
- Differentially Private Reinforcement Learning with Self-Play (NeurIPS 2024 · similarity 0.87)
- Exactly Minimax-Optimal Locally Differentially Private Sampling (NeurIPS 2024 · similarity 0.86)
- Shifted Interpolation for Differential Privacy (ICML 2024 · 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.