RewardsOfSum: Exploring Reinforcement Learning Rewards for Summarisation.
Jacob ParnellInigo Jauregi UnanueMassimo PiccardiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- state space
- function approximation
- model free
- temporal difference
- reinforcement learning algorithms
- transfer learning
- multi agent
- dynamic programming
- learning algorithm
- reward function
- supervised learning
- learning problems
- optimal policy
- reinforcement learning methods
- robotic control
- machine learning
- learning process
- learning classifier systems
- sentiment classification
- free text
- complex domains
- robot control
- temporal difference learning
- e learning
- reward shaping
- genetic algorithm