Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts

Authors: Weinan Zhang, Xihuai Wang, Jian Shen, Ming Zhou

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical experiments on competitive and cooperative tasks demonstrate that AORPO can achieve improved sample efficiency with comparable asymptotic performance over the compared MARL methods.
Researcher Affiliation Academia Weinan Zhang , Xihuai Wang , Jian Shen , Ming Zhou Shanghai Jiao Tong University {wnzhang, leoxhwang, r ocky, mingak}@sjtu.edu.cn
Pseudocode Yes Algorithm 1: AORPO Algorithm
Open Source Code No No explicit statement providing concrete access to source code (e.g., repository link, explicit code release statement) for the methodology described in this paper was found.
Open Datasets Yes Based on a multi-agent particle environment, we evaluate our method in two types of cooperative tasks... Multi-Agent Particle Environment [Lowe et al., 2017]
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 into train/validation/test sets.
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 algorithms like MASAC and MADDPG but does not provide specific software names with version numbers (e.g., Python 3.8, PyTorch 1.9) needed to replicate the experiment.
Experiment Setup Yes Other implementation details, including network architectures and important hyperparameters, are provided in Appendix F.