Action Semantics Network: Considering the Effects of Actions in Multiagent Systems

Authors: Weixun Wang, Tianpei Yang, Yong Liu, Jianye Hao, Xiaotian Hao, Yujing Hu, Yingfeng Chen, Changjie Fan, Yang Gao

ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on Star Craft II micromanagement and Neural MMO show ASN significantly improves the performance of state-of-the-art DRL approaches compared with several network architectures.
Researcher Affiliation Collaboration Weixun Wang1 , Tianpei Yang1 , Yong Liu2, Jianye Hao1,3,4 , Xiaotian Hao1, Yujing Hu5, Yingfeng Chen5, Changjie Fan5, Yang Gao2 {wxwang, tpyang}@tju.edu.cn, lucasliunju@gmail.com, {jianye.hao, xiaotianhao}@tju.edu.cn, {huyujing, chenyingfeng1, fanchangjie}@corp.netease.com, gaoy@nju.edu.cn 1College of Intelligence and Computing, Tianjin University 2Nanjing University 3Tianjin Key Lab of Machine Learning, Tianjin University 4Noah s Ark Lab, Huawei 5Net Ease Fuxi AI Lab
Pseudocode No The paper does not contain any clearly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes More details can be found at https://sites.google.com/view/iclrasn, the source code is put on https://github.com/MAS-anony/ASN
Open Datasets Yes Experimental results on Star Craft II micromanagement (Samvelyan et al., 2019) and Neural MMO (Suarez et al., 2019) show our ASN leads to better performance compared with state-of-the-art approaches in terms of both convergence speed and final performance.
Dataset Splits No The paper describes hyperparameters and game scenarios but does not explicitly provide training/validation/test dataset splits (e.g., percentages, sample counts, or citations to predefined splits for data partitioning).
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions optimizers (RMSProp, Adam) and specific DRL algorithms (PPO, ACKTR, A2C, QMIX, VDN), but does not provide version numbers for any software dependencies, libraries, or frameworks used in the implementation.
Experiment Setup Yes Here we provide the hyperparameters for Star Craft II shown in Table 2.