Reward Function Learning for Q-learning-Based Geographic Routing Protocol.
Weiqi JinRentao GuYuefeng JiPublished in: IEEE Commun. Lett. (2019)
Keyphrases
- reinforcement learning
- routing protocol
- learning algorithm
- reward function
- reinforcement learning algorithms
- hierarchical reinforcement learning
- prior knowledge
- inverse reinforcement learning
- state space
- cooperative
- sensor networks
- markov chain
- optimal policy
- network topology
- mobile ad hoc networks
- dynamic programming
- state action