Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning
Authors: Zhiwei Xu, dapeng li, Bin Zhang, Yuan Zhan, Yunpeng Baiia, Guoliang Fan
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental results show that our method improves the sample efficiency in different partially observable Markov decision process domains. |
| Researcher Affiliation | Academia | Zhiwei Xu, Dapeng Li, Bin Zhang, Yuan Zhan, Yunpeng Bai, Guoliang Fan Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences {xuzhiwei2019, lidapeng2020, zhangbin2020, zhanyuan2020, baiyuanpeng2020, guoliang.fan}@ia.ac.cn |
| Pseudocode | No | The paper does not contain a clearly labeled 'Pseudocode' or 'Algorithm' block. |
| Open Source Code | Yes | 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 | Finally, we evaluated the performance of MBVD in several different domains, including Star Craft II [41], Google Research Football [26] and Multi-Agent Mu Jo Co [37]. |
| Dataset Splits | No | The main body of the paper mentions using various experimental domains (Star Craft II, Google Research Football, Multi-Agent Mu Jo Co) but does not explicitly provide specific percentages, counts, or methodologies for training, validation, and test dataset splits. The ethics statement section 3(b) indicates 'Yes' for specifying 'data splits' and points to 'Appendix ??', but these details are not present in the main text provided. |
| Hardware Specification | No | The main body of the paper does not contain specific hardware details such as GPU models, CPU types, or memory specifications used for running experiments. The ethics statement section 3(d) indicates 'Yes' for including 'type of resources used' and points to 'Appendix ??', but these details are not present in the main text provided. |
| Software Dependencies | No | The paper does not explicitly provide specific software dependencies, such as library names with version numbers, needed to replicate the experiments. |
| Experiment Setup | No | The main body of the paper states 'The details of all experiments can be found in Appendix ??' and the ethics statement section 3(b) indicates 'Yes' for specifying 'training details (e.g., data splits, hyperparameters, how they were chosen)', but these specific details are not present within the main text provided. |