Distributed Emergent Agreements with Deep Reinforcement Learning.
Kyrill SchmidRobert MüllerLenz BelznerJohannes TochtermannClaudia Linnhoff-PopienPublished in: IJCNN (2021)
Keyphrases
- reinforcement learning
- multi agent
- distributed systems
- peer to peer
- cooperative
- state space
- model free
- function approximation
- lightweight
- temporal difference
- loosely coupled
- computer networks
- distributed environment
- optimal policy
- web services
- information systems
- learning algorithm
- temporal difference learning
- real time
- multi agent reinforcement learning
- reinforcement learning algorithms
- distributed data
- optimal control
- neural network