Leveraging Deep Reinforcement Learning for Pedagogical Policy Induction in an Intelligent Tutoring System.
Markel Sanz AusinHamoon AzizsoltaniTiffany BarnesMin ChiPublished in: EDM (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- learning process
- policy gradient
- function approximators
- partially observable environments
- reinforcement learning problems
- actor critic
- reinforcement learning algorithms
- markov decision problems
- function approximation
- partially observable
- state space
- control policy
- partially observable domains
- e learning
- action space
- long run
- markov decision processes
- approximate dynamic programming
- state and action spaces
- learning environment
- state action
- machine learning
- reward function
- model free
- dynamic programming
- inductive inference
- policy evaluation
- intelligent tutoring systems
- average reward
- control policies
- partially observable markov decision processes
- continuous state spaces
- policy iteration
- transition model
- inverse reinforcement learning
- policy gradient methods
- inductive logic programming
- learning algorithm
- finite state
- reinforcement learning methods
- continuous state
- temporal difference
- tutoring system
- collaborative learning
- learning objects
- state dependent
- learning analytics
- inductive learning
- rl algorithms
- learning problems
- transfer learning
- learning experience
- agent learns
- mobile robot