Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used
evaluation tasks and criteria, making comparisons between approaches difficult. In this work …

Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and
has made progress in various fields. Specifically, cooperative MARL focuses on training a …

This review addresses the problem of learning abstract representations of the measurement
data in the context of Deep Reinforcement Learning (DRL). While the data are often …

Diffusion model (DM) recently achieved huge success in various scenarios including offline
reinforcement learning, where the diffusion planner learn to generate desired trajectories …

Ad hoc teamwork is the research problem of designing agents that can collaborate with new
teammates without prior coordination. This survey makes a two-fold contribution: First, it …

Ad hoc teamwork is the well-established research problem of designing agents that can
collaborate with new teammates without prior coordination. This survey makes a two-fold …

Robustly cooperating with unseen agents and human partners presents significant
challenges due to the diverse cooperative conventions these partners may adopt. Existing …

Training a robust cooperative agent requires diverse partner agents. However, obtaining
those agents is difficult. Previous works aim to learn diverse behaviors by changing the state …

对手建模作为多智能体博弈对抗的关键技术, 是一种典型的智能体认知行为建模方法.
介绍了多智能体博弈对抗几类典型模型, 非平稳问题和元博弈相关理论; 梳理总结对手建模方法 …

In cooperative multi-agent reinforcement learning (MARL), where agents only have access
to partial observations, efficiently leveraging local information is critical. During long-time …