Evaluating Meta-Reinforcement Learning through a HVAC Control Benchmark (Student Abstract).
Yashvir S. GrewalFrits de NijsSarah GoodwinPublished in: AAAI (2021)
Keyphrases
- reinforcement learning
- control problems
- learning process
- optimal control
- robot control
- control system
- student learning
- learning environment
- real world
- adaptive control
- control strategy
- markov decision processes
- intelligent tutoring systems
- learning styles
- higher level
- high level
- temporal difference
- neural network
- control policy
- optimal policy
- function approximation
- student model
- control strategies
- science education
- knowledge level
- learning algorithm
- multiple choice