Natural Language Generation as Planning under Uncertainty Using Reinforcement Learning.
Verena RieserOliver LemonPublished in: CoRR (2016)
Keyphrases
- natural language generation
- planning under uncertainty
- reinforcement learning
- markov decision processes
- partially observable markov decision processes
- multi agent
- natural language
- decision theoretic
- optimal policy
- dialogue system
- robotic tasks
- text generation
- state space
- natural language processing
- machine translation
- belief space
- dialog systems
- ai planning
- word order
- finite state
- learning algorithm
- dynamical systems
- partially observable
- dynamic programming
- orders of magnitude
- optimal control
- multi agent systems
- partially observable markov decision process
- reward function
- infinite horizon