Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
Authors: Fengzhuo Zhang, Boyi Liu, Kaixin Wang, Vincent Tan, Zhuoran Yang, Zhaoran Wang
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the performance of the algorithms on the Multiple Particle Environment (MPE) [44, 45]. We focus on the cooperative navigation task, where N agents move cooperatively to cover L landmarks in an environment. (...) Figure 3 shows that the performances of the MLP and deep sets are worse than that of the set transformer. |
| Researcher Affiliation | Academia | National University of Singapore Northwestern University Yale University {fzzhang, kaixin.wang}@u.nus.edu, boyiliu2018@u.northwestern.edu, vtan@nus.edu.sg, zhuoranyang.work@gmail.com, zhaoranwang@gmail.com |
| Pseudocode | No | The paper describes algorithms formally using mathematical equations (e.g., Eqn. 1 and Eqn. 3) but does not include structured pseudocode blocks or algorithms explicitly labeled as 'Algorithm' or 'Pseudocode'. |
| Open Source Code | Yes | 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] |
| Open Datasets | Yes | We evaluate the performance of the algorithms on the Multiple Particle Environment (MPE) [44, 45]. |
| Dataset Splits | No | The paper states that an offline dataset was collected but does not provide specific details on how it was split into training, validation, and test sets (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper describes the experiments but does not provide specific details about the hardware used (e.g., GPU/CPU models, memory, or cloud instance types). |
| Software Dependencies | No | The paper states 'For the implementation details, please refer to Appendix O,' but Appendix O is not provided in the given text. Thus, specific software dependencies with version numbers are not available in the main body. |
| Experiment Setup | No | The paper states 'For the implementation details, please refer to Appendix O,' but Appendix O is not provided in the given text. The main body does not contain specific hyperparameters, learning rates, batch sizes, or other explicit configuration steps for the experimental setup. |