Deep Reinforcement Learning for Multiple Agents in a Decentralized Architecture: A Case Study in the Telecommunication Domain.
Hongyi ZhangJingya LiZhiqiang Tyler QiAnders AronssonJan BoschHelena Holmström OlssonPublished in: ICSA-C (2023)
Keyphrases
- multiple agents
- multi agent
- reinforcement learning
- single agent
- reward function
- multi agent coordination
- management system
- diagnostic problem solving
- case study
- cooperative
- domain specific
- machine learning
- transfer learning
- agent societies
- learning capabilities
- autonomous agents
- optimal policy
- learning process
- search space
- learning algorithm
- markov decision processes
- test bed
- temporal difference
- multiagent systems
- peer to peer
- mobile communication
- dec pomdps