Cooperative retransmissions using Markov decision process with reinforcement learning.
Ghasem Naddafzadeh ShiraziPeng Yong KongChen-Khong ThamPublished in: PIMRC (2009)
Keyphrases
- markov decision process
- cooperative
- reinforcement learning
- state space
- optimal policy
- markov decision processes
- temporal difference learning
- multi agent
- policy iteration
- action space
- function approximation
- infinite horizon
- finite horizon
- initial state
- markov games
- control problems
- reward function
- state action
- partial observability
- reinforcement learning algorithms
- temporal difference
- model free
- multi agent systems
- game theory
- machine learning