Fast Task-Adaptation for Tasks Labeled Using Natural Language in Reinforcement Learning.
Matthias Hutsebaut-BuysseKevin MetsSteven LatréPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- natural language
- adaptation process
- supervised learning
- learning algorithm
- knowledge representation
- machine learning
- transfer learning
- natural language processing
- real robot
- function approximation
- multi task
- multiple tasks
- state space
- mobile robot
- optimal control
- complex domains
- multi agent
- natural language interface
- e learning
- multi agent environments