Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation.
Yang GaoChristian M. MeyerMohsen MesgarIryna GurevychPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- learning algorithm
- learning problems
- eligibility traces
- learning tasks
- online learning
- information retrieval
- learning process
- function approximation
- supervised learning
- active learning
- optimal policy
- state space
- multi agent
- dynamic programming
- learning capabilities
- temporal difference learning
- retrieval systems
- transfer learning
- long run
- reinforcement learning algorithms
- reinforcement learning methods
- rl algorithms