.png){kind=icon}
返回
When to Switch: Planning and Learning for Partially Observable Multi-Agent Pathfinding
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2023.3303502.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-agent pathfinding (MAPF) is a problem that involves finding a set of non-conflicting paths for a set of agents confined to a graph. In this work, we study a MAPF setting, where the environment is only partially observable for each agent, i.e., an agent observes the obstacles and other agents only within a limited field-of-view. Moreover, we assume that the agents do not communicate and do not share knowledge on their goals, intended actions, etc. The task is to construct a policy that maps the agent's observations to actions. Our contribution is multifold. First, we propose two novel policies for solving partially observable MAPF (PO-MAPF): one based on heuristic search and another one based on reinforcement learning (RL). Next, we introduce a mixed policy that is based on switching between the two. We suggest three different switch scenarios: the heuristic, the deterministic, and the learnable one. A thorough empirical evaluation of all the proposed policies in a variety of setups shows that the mixing policy demonstrates the best performance is able to generalize well to the unseen maps and problem instances, and, additionally, outperforms the state-of-the-art counterparts (Primal2 and PICO). The source-code is available at https://github.com/AIRI-Institute/when-to-switch.
Keyword:
Multi-agent pathfinding (MAPF)
planning
partially observable MAPF (PO-MAPF)
reinforcement learning (RL)
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Does it take older adults longer than younger adults to perceptually segregate a speech target from a background masker?在感知上将语音目标与背景掩蔽器隔离开来是否需要老年人比年轻人更长的时间？
PREAI
分享收藏Efeito da incorporação de lodo de ETA contendo alto teor de ferro em cerâmica argilosa.png)
Cerâmica
OAAI
CerâmicaIF0
OAAI分享收藏
查看更多内容