From Few to More: Large-Scale Dynamic Multiagent Curriculum Learning
Authors: Weixun Wang, Tianpei Yang, Yong Liu, Jianye Hao, Xiaotian Hao, Yujing Hu, Yingfeng Chen, Changjie Fan, Yang Gao7293-7300
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that Dy MA-CL using Dy AN greatly improves the performance of large-scale multiagent learning compared with state-of-the-art deep reinforcement learning approaches. We also investigate the influence of three transfer mechanisms across curricula through extensive simulations. |
| Researcher Affiliation | Collaboration | Weixun Wang,1 Tianpei Yang,1 Yong Liu,2 Jianye Hao,1,3 Xiaotian Hao,1 Yujing Hu,4 Yingfeng Chen,4 Changjie Fan,4 Yang Gao2 1College of Intelligence and Computing, Tianjin University, {wxwang, tpyang, jianye.hao, xiaotianhao}@tju.edu.cn 2National Key Laboratory for Novel Software Technology, Nanjing University, lucasliunju@gmail.com, gaoy@nju.edu.cn 3Noah s Ark Lab, Huawei 4Net Ease Fuxi AI Lab, {huyujing, chenyingfeng1, fanchangjie}@corp.netease.com |
| Pseudocode | No | The paper describes the proposed methods in text but does not include any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | No | The paper does not include an explicit statement about releasing source code or a link to a code repository for the methodology described. |
| Open Datasets | Yes | We evaluate the performance of our Dy MA-CL on two large-scale scenarios: 1) Star Craft II, which contains various scenarios for a number of agents to learn coordination to solve complex tasks; and 2) MAgent (Zheng et al. 2018), which is a simulated battlefield with two large-scale armies (groups), e.g., each army consists of 50 soldiers who would be arrayed in the battlefield (a grid world). |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions various DRL algorithms but does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | No | The paper states that 'The details of neural network structures, parameter settings and the curriculum schedule are in the ar Xiv version,' but it does not provide specific experimental setup details, such as concrete hyperparameter values or training configurations, within the main text. |