Twin attentive deep reinforcement learning for multi-agent defensive convoy.
Dongyu FanHaikuo ShenLijing DongPublished in: Int. J. Mach. Learn. Cybern. (2023)
Keyphrases
- reinforcement learning
- multi agent
- moving object trajectories
- multi agent environments
- function approximation
- multi agent reinforcement learning
- state space
- traffic signal control
- reinforcement learning agents
- multiagent systems
- cooperative
- multiple agents
- single agent
- multi agent systems
- model free
- optimal policy
- trajectory data
- visual attention
- pre attentive
- learning algorithm
- multiagent reinforcement learning
- autonomous agents
- query language
- reward function
- reinforcement learning algorithms
- learning agent
- mobile robot
- dynamic programming