Reorganization of Agent Networks with Reinforcement Learning Based on Communication Delay.
Kazuki UrakawaToshiharu SugawaraPublished in: IAT (2012)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- learning agent
- multi agent systems
- autonomous learning
- intelligent agents
- learning capabilities
- multiagent systems
- multi agent environments
- agent receives
- agent architecture
- network structure
- markov decision process
- decision making
- social networks
- cooperative
- function approximation
- agent model
- temporal difference
- exploration strategy
- single agent
- learning agents
- reinforcement learning algorithms
- software agents
- agent learns
- robocup soccer
- multiagent reinforcement learning
- reinforcement learning agents
- multiple agents
- state action
- function approximators
- reward function
- neural network
- computer networks
- complex systems
- optimal policy
- learning algorithm
- machine learning