Multimodal Knowledge Alignment with Reinforcement Learning.
Youngjae YuJiwan ChungHeeseung YunJack HesselJae Sung ParkXiming LuPrithviraj AmmanabroluRowan ZellersRonan Le BrasGunhee KimYejin ChoiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- knowledge acquisition
- knowledge base
- neural network
- expert systems
- knowledge representation
- knowledge extraction
- learning systems
- knowledge management
- temporal difference
- image alignment
- machine learning
- reinforcement learning algorithms
- dynamic time warping
- function approximation
- knowledge sharing
- background knowledge
- optimal policy
- knowledge based systems
- collaborative learning
- state space
- knowledge discovery
- domain knowledge
- multi agent
- metadata
- genetic algorithm