Deep Reinforcement Learning Based Beamforming in RIS-Assisted MIMO System Under Hardware Loss.
Yuan SunZhiquan BaiJinqiu ZhaoDejie MaZhaoxia XianKyung Sup KwakPublished in: ICACT (2024)
Keyphrases
- reinforcement learning
- multiple input multiple output
- vlsi architecture
- hardware and software
- low cost
- function approximation
- linear array
- state space
- communication systems
- vlsi implementation
- computer systems
- mimo systems
- reinforcement learning algorithms
- temporal difference learning
- machine learning
- multi input multi output
- learning algorithm
- hardware implementation
- model free
- dynamic programming
- frequency domain
- massively parallel
- processing elements
- wireless channels
- temporal difference
- hardware architecture
- fading channels
- bit error rate
- markov decision processes
- channel estimation
- multiple input
- robot control
- optimal policy
- cdma systems
- multi agent