Photonic architecture for reinforcement learning.
Fulvio FlaminiArne HamannSofiène JerbiLea M. TrenkwalderHendrik Poulsen NautrupHans J. BriegelPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- software architecture
- management system
- real time
- learning capabilities
- multi agent
- reference model
- state space
- architectural design
- distributed architecture
- neural network
- model free
- design considerations
- temporal difference learning
- master slave
- layered architecture
- multi agent reinforcement learning
- transfer learning
- optimal policy
- website
- learning algorithm
- data mining
- databases