Multi-Actor-Attention-Critic Reinforcement Learning for Central Place Foraging Swarms.
Ning YangQi LuKele XuBo DingZijian GaoPublished in: IJCNN (2021)
Keyphrases
- reinforcement learning
- temporal difference
- function approximation
- swarm intelligence
- actor critic
- reinforcement learning algorithms
- ant colonies
- learning algorithm
- particle swarm optimization
- machine learning
- dynamic environments
- evaluation function
- state space
- bio inspired
- cooperative
- step size
- gradient method
- policy gradient
- real robot
- collective behavior
- temporal difference learning
- monte carlo
- learning process
- multi agent systems
- multi agent simulation
- honey bee
- foraging theory