Multi-Agent Proximal Policy Optimization for a Deadlock Capable Transport System in a Simulation-Based Learning Environment.
Marcel MüllerTobias ReggelinHartmut ZadekLorena S. Reyes-RubianoPublished in: WSC (2023)
Keyphrases
- multi agent
- learning environment
- optimization algorithm
- optimization problems
- global optimization
- multi agent systems
- learning activities
- optimal policy
- constrained optimization
- intelligent agents
- multiagent systems
- optimization process
- multiple agents
- machine learning
- optimization method
- learning systems
- e learning