ERLP: Ensembles of Reinforcement Learning Policies (Student Abstract).
Rohan SaphalBalaraman RavindranDheevatsa MudigereSasikanth AvanchaBharat KaulPublished in: AAAI (2020)
Keyphrases
- reinforcement learning
- optimal policy
- learning process
- policy search
- markov decision process
- control policies
- learning environment
- function approximation
- student learning
- reinforcement learning agents
- intelligent tutoring systems
- markov decision processes
- reward function
- state space
- dynamic programming
- student model
- knowledge level
- tutoring system
- partially observable markov decision processes
- control policy
- markov decision problems
- fitted q iteration
- decision trees
- decision problems
- high level
- machine learning
- ensemble learning
- hierarchical reinforcement learning
- supervised learning
- learning styles
- reinforcement learning algorithms
- model free
- long run
- online course
- high school students
- optimal control
- temporal abstractions
- random forests
- neural network
- ensemble methods
- learning problems
- transfer learning
- average reward
- undergraduate students
- continuous state
- state abstraction
- neural network ensemble