A Dual-Memory Architecture for Reinforcement Learning on Neuromorphic Platforms.
Wilkie Olin-AmmentorpYury SokolovMaxim BazhenovPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- software platform
- learning capabilities
- computing power
- memory usage
- real time
- associative memory
- learning algorithm
- memory management
- function approximation
- management system
- software architecture
- optimal policy
- event driven
- state space
- reinforcement learning algorithms
- processing elements
- memory size
- multi agent
- middleware architecture