A Proximity-Based Q-Learning Reward Function for Femtocell Networks.
Jonathan R. TefftNicholas J. KirschPublished in: VTC Fall (2013)
Keyphrases
- reward function
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- optimal policy
- hierarchical reinforcement learning
- inverse reinforcement learning
- partially observable
- transition probabilities
- multiple agents
- markov decision process
- initially unknown
- state action
- learning agent
- function approximation
- generative model
- social networks
- control policies
- transition model
- state variables
- machine learning
- graphical models
- markov decision problems