When to Intervene: Toward a Markov Decision Process Dialogue Policy for Computer Science Tutoring.
Christopher Michael MitchellKristy Elizabeth BoyerJames C. LesterPublished in: AIED Workshops (2013)
Keyphrases
- computer science
- optimal policy
- natural language dialogue
- markov decision process
- reward function
- lecture notes
- tutorial dialogue
- inverse reinforcement learning
- control policy
- spoken dialogue
- tutoring system
- intelligent tutoring systems
- state space
- decision problems
- social sciences
- markov decision processes
- computer scientists
- finite state
- long run
- mixed initiative
- dialogue management
- electrical engineering
- information sciences
- intelligent tutoring
- natural language
- dialogue system
- infinite horizon
- partially observable markov decision process
- applied mathematics
- computer science education
- artificial intelligence
- data mining
- human machine
- man machine
- conversational agent
- partially observable
- student model
- researchers and practitioners
- markov chain
- dynamic programming
- reinforcement learning
- spoken dialogue systems
- management science
- selected papers
- semi autonomous
- computer science students