FPGA Divide-and-Conquer Placement using Deep Reinforcement Learning.
Shang WangDeepak Ranganatha Sastry MamillapalliTianpei YangMatthew E. TaylorPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- field programmable gate array
- reinforcement learning algorithms
- high speed
- model free
- real time image processing
- hardware design
- real time
- machine learning
- optimal policy
- markov decision processes
- signal processing
- temporal difference learning
- optimal control
- state space
- digital signal
- transfer learning
- learning algorithm
- dedicated hardware
- deep learning
- learning process
- dynamic programming
- robotic control
- fpga implementation
- fpga hardware
- verilog hdl
- software implementation
- function approximators
- temporal difference
- hardware implementation
- learning problems
- low cost