Multifidelity Reinforcement Learning With Gaussian Processes: Model-Based and Model-Free Algorithms.
Varun SuryanNahush GondhalekarPratap TokekarPublished in: IEEE Robotics Autom. Mag. (2020)
Keyphrases
- model free
- reinforcement learning
- gaussian processes
- policy iteration
- function approximation
- reinforcement learning algorithms
- rl algorithms
- temporal difference
- policy evaluation
- gaussian process
- markov decision processes
- supervised learning
- state space
- gaussian process regression
- machine learning
- bayesian framework
- multi task
- optimal policy
- non stationary
- text mining
- training data