Injecting Prior Knowledge for Transfer Learning into Reinforcement Learning Algorithms using Logic Tensor Networks.
Samy BadreddineMichael SprangerPublished in: NeSy@IJCAI (2019)
Keyphrases
- transfer learning
- reinforcement learning algorithms
- reinforcement learning
- prior knowledge
- labeled data
- learning tasks
- tabula rasa
- learning algorithm
- function approximation
- model free
- state space
- cross domain
- markov decision processes
- temporal difference
- knowledge transfer
- multi task
- semi supervised learning
- unlabeled data
- reinforcement learning methods
- machine learning
- active learning
- learning process
- dynamic programming
- supervised learning
- semi supervised
- data sets
- network structure
- optimal policy
- collaborative filtering
- higher order
- target domain
- text classification
- training data
- text categorization
- text mining
- reward function
- information retrieval
- transfer knowledge