RLPlace: Using Reinforcement Learning and Smart Perturbations to Optimize FPGA Placement.
Mohamed A. ElgammalKevin E. MurrayVaughn BetzPublished in: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. (2022)
Keyphrases
- reinforcement learning
- high speed
- function approximation
- hardware implementation
- signal processing
- real time image processing
- image processing
- state space
- temporal difference
- markov decision processes
- model free
- robotic control
- temporal difference learning
- software implementation
- field programmable gate array
- learning problems
- low cost
- supervised learning
- hardware design
- multi agent
- multi agent reinforcement learning
- real time
- optimal control
- action selection
- smart grid
- dynamic programming
- learning algorithm
- fpga implementation
- policy search
- digital signal
- smart objects