A Polytomous Computerized-Adaptive Testing that Rewards Partial Knowledge.
Yung-Chin YenRong-Guey HoLi-Ju ChenPublished in: ICCE (2006)
Keyphrases
- partial knowledge
- computerized adaptive testing
- learning environment
- reinforcement learning
- multiarmed bandit
- markov decision processes
- free riding
- bandit problems
- reward signal
- long term and short term
- multi armed bandits
- belief state
- credit assignment
- domain knowledge
- complex systems
- reward function
- neural network