Hardware Accelerator for Capsule Network based Reinforcement Learning.
Dola RamSuraj PanwarKuruvilla VarghesePublished in: VLSID (2022)
Keyphrases
- reinforcement learning
- field programmable gate array
- hardware and software
- low cost
- function approximation
- real time
- hardware implementation
- temporal difference learning
- vlsi implementation
- learning algorithm
- reinforcement learning algorithms
- embedded systems
- model free
- state space
- optimal policy
- endoscopic images
- computing systems
- temporal difference
- massively parallel
- hardware design
- data mining
- computer systems
- supervised learning
- dynamic programming
- multi agent
- machine learning
- parallel implementation
- transfer learning
- multi agent reinforcement learning
- parallel hardware