IRS-assisted anti-jamming communication based on action space smooth Q-learning.
Yang LiuKui XuNan MaMi ZhangChengqian MaYueyue ZhangPublished in: IECC (2023)
Keyphrases
- action space
- state space
- reinforcement learning
- state action
- action selection
- state information
- continuous state spaces
- reinforcement learning methods
- continuous state
- markov decision processes
- real valued
- single agent
- state and action spaces
- dynamic programming
- multi agent
- function approximation
- heuristic search
- function approximators
- temporal difference
- cooperative
- markov chain
- optimal policy
- dynamical systems
- reinforcement learning algorithms
- stochastic processes
- learning agent
- markov decision process
- partially observable
- dynamic environments
- belief state
- multi agent systems
- state variables