Speeding up Vision Transformers Through Reinforcement Learning.
Francesco CauteruccioMichele MarchettiDavide TrainiDomenico UrsinoLuca VirgiliPublished in: SEBD (2024)
Keyphrases
- reinforcement learning
- computer vision
- function approximation
- reinforcement learning algorithms
- optimal policy
- image processing
- vision system
- robotic control
- control problems
- markov decision processes
- dynamic programming
- learning process
- search algorithm
- real time
- state space
- expert systems
- model free
- active vision
- database
- learning algorithm
- temporal difference
- neural network
- function approximators
- multi agent reinforcement learning