Polynomial Time Reinforcement Learning in Correlated FMDPs with Linear Value Functions.
Siddartha DevicZihao DengBrendan JubaPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- special case
- linear functions
- markov decision processes
- function approximation
- hilbert space
- nonlinear functions
- linear constraints
- reinforcement learning algorithms
- approximation algorithms
- state space
- computational complexity
- learning algorithm
- neural network
- optimal control
- worst case
- function approximators
- temporal difference learning
- reinforcement learning methods
- machine learning