CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning.
Siddharth VermaJustin FuSherry YangSergey LevinePublished in: NAACL-HLT (2022)
Keyphrases
- reinforcement learning
- dialogue system
- tutorial dialogue
- artificial intelligence
- dialogue management
- machine learning
- human computer
- function approximation
- natural language
- ai systems
- real time
- expert systems
- state space
- temporal difference
- markov decision processes
- optimal policy
- human machine
- multi agent
- spoken dialogue systems
- case based reasoning
- knowledge representation
- lecture notes in artificial intelligence
- natural language dialogue
- mixed initiative
- reinforcement learning algorithms
- model free
- intelligent systems
- learning algorithm
- optimal control
- conversational agent
- online discussion forums
- action selection
- robot control
- intelligent tutoring systems
- knowledge based systems
- dynamic programming
- ai methods
- learning process
- ai researchers
- computer science
- turn taking