Reinforcement learning for multi-agent formation navigation with scalability.
Yalei GongHongyun XiongMengMeng LiHaibo WangXiaohong NianPublished in: Appl. Intell. (2023)
Keyphrases
- reinforcement learning
- multi agent
- multi agent environments
- function approximation
- group formation
- temporal difference
- model free
- single agent
- indoor environments
- learning agents
- multiagent systems
- multi agent reinforcement learning
- multi agent systems
- cooperative
- markov decision processes
- fault tolerance
- reinforcement learning agents
- reinforcement learning algorithms
- supervised learning
- state space
- agent oriented
- multiple agents
- navigation systems
- coalition formation
- software agents
- autonomous agents
- transfer learning
- intelligent agents
- learning process
- information space
- obstacle avoidance
- machine learning
- optimal control
- outdoor environments
- agent behavior
- heterogeneous agents
- dynamic programming
- robotic control
- traffic signal control