A Space-Efficient Technique of Policy Trees for an Intelligent Tutoring System on POMDP.
Fangju WangPublished in: CSEDU (Selected Papers) (2018)
Keyphrases
- space efficient
- optimal policy
- model free reinforcement learning
- partially observable markov decision processes
- markov decision process
- partially observable
- partially observable markov decision process
- data structure
- reinforcement learning
- markov decision problems
- policy evaluation
- data streams
- state space
- sliding window
- markov decision processes
- infinite horizon
- decision trees
- dynamic programming
- decision problems
- finite state
- range sum queries
- reward function
- belief state
- intelligent tutoring systems
- dynamical systems
- b tree
- point based value iteration
- multi agent
- continuous state
- policy iteration
- tree structure
- decision theoretic
- state dependent
- suffix array
- control policies
- data sets
- database management systems
- bloom filter
- policy gradient
- long run
- uncertain data streams
- linear space
- databases