Addressing Signal Delay in Deep Reinforcement Learning.
William Wei WangDongqi HanXufang LuoDongsheng LiPublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- signal processing
- non stationary
- model free
- state space
- reinforcement learning algorithms
- function approximation
- frequency domain
- temporal difference
- markov decision processes
- high frequency
- impulse response
- machine learning
- policy search
- dynamic programming
- original signal
- signal detection
- multi agent reinforcement learning
- received signal
- real time
- critical path
- robotic control
- deep learning
- action selection
- optimal control
- image compression
- learning process
- neural network
- data sets