Synthesising Reward Machines for Cooperative Multi-Agent Reinforcement Learning.
Giovanni VarricchioneNatasha AlechinaMehdi DastaniBrian LoganPublished in: EUMAS (2023)
Keyphrases
- multi agent reinforcement learning
- reinforcement learning
- cooperative
- learning agent
- multi agent
- learning agents
- multi agent systems
- multi agent learning
- stochastic games
- state space
- reward function
- machine learning
- distributed control
- function approximation
- sufficient conditions
- supervised learning
- control system
- knowledge base
- neural network