DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning
Authors: Canzhe Zhao, Yanjie Ze, Jing Dong, Baoxiang Wang, Shuai Li
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate a clear advantage of DPMAC over baseline methods in privacy-preserving scenarios.Extensive experiments are conducted in multi-agent particle environment (MPE) [Lowe et al., 2017], including cooperative navigation, cooperative communication and navigation, and predatorprey tasks. Specifically, in privacy-preserving scenarios, DPMAC significantly outperforms baselines. Moreover, even without any privacy constraints, DPMAC could also gain competitive performance against baselines. |
| Researcher Affiliation | Academia | 1John Hopcroft Center for Computer Science, Shanghai Jiao Tong University 2Department of Computer Science and Engineering, Shanghai Jiao Tong University 3School of Data Science, The Chinese University of Hong Kong, Shenzhen {canzhezhao, zeyanjie, shuaili8}@sjtu.edu.cn, jingdong@link.cuhk.edu.cn, bxiangwang@cuhk.edu.cn |
| Pseudocode | Yes | Please refer to Appendix A and Appendix E for the complete pseudo code of DPMAC, and detailed optimization process of the message senders and receivers, respectively. |
| Open Source Code | No | The paper does not provide any specific link or statement about open-sourcing the code for DPMAC. |
| Open Datasets | Yes | We evaluate the algorithms on the multi-agent particle environment (MPE) [Mordatch and Abbeel, 2017] |
| Dataset Splits | No | The paper mentions evaluating algorithms on the MPE environment but does not specify exact training, validation, and test split percentages or sample counts in the main text. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types, memory) used to run the experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies (e.g., Python, PyTorch, TensorFlow, or specific libraries). |
| Experiment Setup | Yes | In particular, Figure 2b and 2c show the performance under the privacy budget ϵ = 0.10, 1.0 and both with δ = 10-4. Please see Appendix E for more training details. |