Towards Abstractive Timeline Summarisation Using Preference-Based Reinforcement Learning.
Yuxuan YeEdwin SimpsonPublished in: ECAI (2023)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- model free
- state space
- reinforcement learning algorithms
- learning algorithm
- case study
- optimal control
- markov decision processes
- temporal difference learning
- control problems
- action selection
- multi agent
- machine learning
- direct policy search
- multi agent reinforcement learning
- learning problems
- learning capabilities
- data sets
- decision making
- information retrieval
- data mining