Reinforcement Learning Hardware Accelerator using Cache-Based Memoization for Optimized Q-Table Selection.
Muhammad Sulthan MazayaEko Mursito BudiInfall SyafalniNana SutisnaTrio AdionoPublished in: COOL CHIPS (2024)
Keyphrases
- reinforcement learning
- embedded processors
- hardware and software
- function approximation
- parallel implementation
- low cost
- real time
- field programmable gate array
- machine learning
- memory hierarchy
- computer systems
- data access
- state space
- parallel architectures
- optimal policy
- parallel processing
- database
- computing systems
- computational power
- temporal difference