Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning.
Mingjie SunJimin XiaoEng Gee LimPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- learning process
- neural network
- model free
- markov decision processes
- action space
- state space
- multi agent
- learning algorithm
- machine learning
- deep learning
- real world
- relational reinforcement learning
- website
- supervised learning
- transfer learning
- data sets
- learning capabilities
- iterative process
- expression recognition
- iterative optimization
- robotic control
- direct policy search