Research map / Federated learning and privacy / Differential privacy
Privacy-Preserving Policy Iteration for Decentralized POMDPs
Feng Wu, Shlomo Zilberstein, Xiaoping Chen
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 privacy protection (Paillier encryption, masking, permutation) to DICE, giving P3I | DICE (CE method for Dec-POMDPs) · 6 Dec-POMDP benchmarks | policy quality | No clear effect |
| add privacy protection (Paillier encryption) to DICE | DICE · Dec-Tiger | runtime (sec.): 3.9 -> 7350 | Hurt |
| add privacy protection to DICE | DICE · Broadcast Channel | runtime (sec.): 4.5 -> 7070 | Hurt |
| add privacy protection to DICE | DICE · Meeting in Grid | runtime (sec.): 11.3 -> 6424 | Hurt |
| add privacy protection to DICE | DICE · Box Pushing | runtime (sec.): 6.1 -> 6907 | Hurt |
| add privacy protection to DICE | DICE · Recycling Robots | runtime (sec.): 4.3 -> 7404 | Hurt |
| add privacy protection to DICE | DICE · Mars Rovers | runtime (sec.): 11.8 -> 6897 | Hurt |
| run encryption/decryption concurrently on 40 cores | P3I · Dec-Tiger | runtime (sec.): 7350 -> 424 | Improved |
| run encryption/decryption concurrently on 40 cores | P3I · Broadcast Channel | runtime (sec.): 7070 -> 433 | Improved |
| run encryption/decryption concurrently on 40 cores | P3I · Meeting in Grid | runtime (sec.): 6424 -> 381 | Improved |
| run encryption/decryption concurrently on 40 cores | P3I · Box Pushing | runtime (sec.): 6907 -> 425 | Improved |
| run encryption/decryption concurrently on 40 cores | P3I · Recycling Robots | runtime (sec.): 7404 -> 433 | Improved |
Closest papers by meaning
- Differentially Private Reinforcement Learning with Self-Play (NeurIPS 2024 · similarity 0.86)
- On the Sample Complexity of Differentially Private Policy Optimization (NeurIPS 2025 · similarity 0.85)
- Optimally Solving Two-Agent Decentralized POMDPs Under One-Sided Information Sharing (ICML 2020 · similarity 0.85)
- Differentially Private Decentralized Learning with Random Walks (ICML 2024 · similarity 0.83)
- The Privacy Power of Correlated Noise in Decentralized Learning (ICML 2024 · similarity 0.82)
- A Surprisingly Simple Continuous-Action POMDP Solver: Lazy Cross-Entropy Search Over Policy Trees (AAAI 2024 · similarity 0.82)
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.
