An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation.
Wanyu DuYangfeng JiPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- imitation learning
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- reinforcement learning methods
- multi agent
- learning algorithm
- markov decision processes
- control problems
- machine learning
- robotic systems
- supervised learning
- dynamic programming
- optimal policy
- humanoid robot
- learning problems
- maximum margin
- semi supervised
- learning capabilities
- single agent