Max-plus approximation for reinforcement learning.
Vinicius Mariano GonçalvesPublished in: Autom. (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- learning algorithm
- approximation error
- approximation algorithms
- neural network
- machine learning
- relative error
- reinforcement learning algorithms
- error bounds
- data mining
- error tolerance
- approximation schemes
- temporal difference
- efficient computation
- optimal control
- markov decision processes
- transfer learning
- markov decision process
- optimal policy
- supervised learning
- approximation methods
- temporal difference learning
- stochastic approximation
- multi agent
- case study
- robotic control