Reinforcement Learning Based Matching for Computation Offloading in D2D Communications.
Bingxin TianLi WangYutong AiAiguo FeiPublished in: ICCC (2019)
Keyphrases
- reinforcement learning
- matching process
- matching algorithm
- function approximation
- learning algorithm
- dynamic programming
- state space
- image matching
- pattern matching
- multi agent reinforcement learning
- graph matching
- learning process
- multi agent
- image sequences
- transfer learning
- image registration
- stereo matching
- point correspondences
- learning problems
- communication systems
- feature matching
- reinforcement learning algorithms
- parallel computation
- computer vision