MORE-3S: Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces.
Tianyu ZhengGe ZhangXingwei QuMing KuangStephen W. HuangZhaofeng HePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- state space
- semantic information
- function approximation
- semantically meaningful
- multimodal interaction
- semantic representation
- multi modal
- reinforcement learning algorithms
- semantic web
- semantic knowledge
- semantic similarity
- model free
- audio visual
- markov decision processes
- domain knowledge
- semantic level
- machine learning
- multimodal information
- semantic features
- wordnet
- co occurrence
- dynamic programming
- high level
- learning algorithm
- genetic algorithm