Modular Networks Prevent Catastrophic Interference in Model-Based Multi-task Reinforcement Learning.
Robin SchiewerLaurenz WiskottPublished in: LOD (2021)
Keyphrases
- multi task
- reinforcement learning
- multi task learning
- transfer learning
- learning problems
- learning tasks
- multitask learning
- multiple tasks
- gaussian processes
- feature selection
- learning algorithm
- network structure
- multi class
- social networks
- machine learning
- supervised learning
- knowledge discovery
- sparse learning
- high order
- prior knowledge
- learning process
- training data