Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Learning Joint Behaviors with Large Variations
Authors: Tianxu Li, Kun Zhu
AAAI 2025 | Venue PDF | LLM Run Details | Input Tokens: 13,735 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 2,911 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the effectiveness of our method by conducting experiments on the LBF, SMAC, and SMACv2 benchmarks. Our method outperforms previous methods in terms of ο¬nal performance and state-action space exploration. |
| Researcher Affiliation | Academia | College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, China EMAIL |
| Pseudocode | Yes | We provide the pseudocode for our method in the Appendix 3. |
| Open Source Code | No | The paper states, "We provide the pseudocode for our method in the Appendix 3." This refers to pseudocode, not runnable source code, and does not provide a direct link or explicit statement of code release. |
| Open Datasets | Yes | We conduct experiments on the Level-Based Foraging (LBF) (Albrecht and Stone 2019), Star Craft Multi Agent Challenge (SMAC) (Samvelyan et al. 2019), and SMACv2 (Ellis et al. 2022) benchmarks to test our proposed DJBD. |
| Dataset Splits | No | The paper uses standard benchmarks like LBF, SMAC, and SMACv2. While it mentions scenarios and random seeds for training, it does not provide specific percentages, sample counts, or detailed methodologies for dataset splits within the main text. |
| Hardware Specification | No | The paper states, "Training details and hyperparameters used in our experiments are available in the Appendix 5." However, no specific hardware details like GPU models, CPU types, or memory are mentioned in the provided main text. |
| Software Dependencies | No | The paper states, "Training details and hyperparameters used in our experiments are available in the Appendix 5." However, no specific software dependencies with version numbers are mentioned in the provided main text. |
| Experiment Setup | No | The paper states, "For a fair comparison, the hyperparameters shared across methods are consistent in each multi-agent task. Training details and hyperparameters used in our experiments are available in the Appendix 5." While hyperparameters exist, they are explicitly mentioned as being in the Appendix and not within the main text provided. |