A M-PSK Timing Recovery Loop Based on Q-Learning.
Gian Carlo CardarilliLuca Di NunzioRocco FazzolariDaniele GiardinoMatteo GuadagnoMarco ReSergio SpanòPublished in: ApplePies (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- cooperative
- function approximation
- traffic signal
- multi agent
- transmission scheme
- multi agent reinforcement learning
- state space
- action selection
- image recovery
- model free
- recovery algorithm
- stochastic approximation
- reinforcement learning algorithms
- machine learning
- learning rate
- optimal policy
- mobile robot
- bucket brigade