Pheromone Based Independent Reinforcement Learning for Multiagent Navigation.
Kaige ZhangYaqing HouHua YuWenxuan ZhuLiang FengQiang ZhangPublished in: NCAA (2021)
Keyphrases
- multi agent
- reinforcement learning
- cooperative
- multiple agents
- state space
- multiagent learning
- ant colony optimization
- learning algorithm
- function approximation
- intelligent agents
- navigation systems
- data sets
- multiagent systems
- multi agent systems
- multi agent reinforcement learning
- continuous state
- reinforcement learning methods
- autonomous agents
- outdoor environments
- temporal difference
- optimal control
- learning problems
- markov decision processes
- optimal policy
- neural network