Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos.
Dongliang HeXiang ZhaoJizhou HuangFu LiXiao LiuShilei WenPublished in: AAAI (2019)
Keyphrases
- natural language descriptions
- reinforcement learning
- natural language
- function approximation
- spatio temporal
- temporal information
- real time
- multi agent reinforcement learning
- optimal policy
- temporal difference
- model free
- markov decision processes
- transfer learning
- reinforcement learning algorithms
- temporal difference learning
- dynamic programming
- learning algorithm
- machine learning
- robotic control
- action selection
- supervised learning
- state space
- learning process
- multi agent
- neural network