TD3lite: FPGA Acceleration of Reinforcement Learning with Structural and Representation Optimizations.
Chan-Wei HuJiang HuSunil P. KhatriPublished in: FPL (2022)
Keyphrases
- reinforcement learning
- temporal difference
- reinforcement learning algorithms
- temporal difference learning
- function approximation
- eligibility traces
- learning algorithm
- real time
- image processing
- neural network
- model free
- markov decision processes
- high speed
- evaluation function
- semantic web
- representation scheme
- multi agent
- real time image processing
- power reduction
- machine learning