Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning.
Leandro M. de LimaRenato A. KrohlingPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- learning process
- reinforcement learning problems
- control policy
- state and action spaces
- control policies
- markov decision processes
- reinforcement learning algorithms
- policy evaluation
- state space
- function approximators
- action space
- partially observable environments
- policy gradient
- function approximation
- partially observable
- real time
- actor critic
- dynamic programming
- learning environment
- intelligent tutoring systems
- policy iteration
- markov decision problems
- state action
- student learning
- reward function
- temporal difference
- average reward
- rl algorithms
- learning styles
- model free
- finite state
- student model
- tutoring system
- continuous state spaces
- inverse reinforcement learning
- partially observable domains
- infinite horizon
- long run
- agent learns
- continuous state
- approximate dynamic programming
- decision problems
- multi agent
- learning algorithm
- reward signal
- university level
- reinforcement learning methods
- state dependent
- control problems
- high school students
- optimal control