Multi-agent assignment via state augmented reinforcement learning.
Leopoldo AgorioSean Van AlenMiguel Calvo-FullanaSantiago PaternainJuan Andrés BazerquePublished in: L4DC (2024)
Keyphrases
- reinforcement learning
- multi agent
- state space
- function approximation
- markov decision processes
- single agent
- partially observable
- traffic signal control
- database
- policy search
- temporal difference learning
- reinforcement learning algorithms
- temporal difference
- optimal policy
- control system
- learning process
- multi agent systems
- learning algorithm