A L-MCRS dynamics approximation by ELM for Reinforcement Learning.
José Manuel López-GuedeBorja Fernández-GaunaJose Antonio Ramos-HernanzPublished in: Neurocomputing (2015)
Keyphrases
- reinforcement learning
- function approximation
- extreme learning machine
- reinforcement learning algorithms
- dynamical systems
- approximation methods
- state space
- dynamic model
- error bounds
- markov decision processes
- optimal policy
- dynamic programming
- action selection
- supervised learning
- multi agent
- robotic control
- machine learning
- model free
- temporal difference
- multi agent reinforcement learning