Learn to Look Around: Deep Reinforcement Learning Agent for Video Saliency Prediction.
Yiran TaoYaosi HuZhenzhong ChenPublished in: VCIP (2021)
Keyphrases
- learning agent
- reinforcement learning
- state space
- solving problems
- learning algorithm
- reinforcement learning algorithms
- learning tasks
- learning process
- learning capabilities
- single agent
- multimedia
- function approximation
- machine learning
- model free
- prediction model
- dynamic programming
- multi agent systems
- multi agent
- artificial intelligence
- markov decision processes
- dynamic environments
- reward function
- mixed initiative