Reinforcement Learning Using a Grid Based Function Approximator.
Alexander SungArtur MerkeMartin A. RiedmillerPublished in: Biomimetic Neural Learning for Intelligent Robots (2005)
Keyphrases
- function approximators
- reinforcement learning
- function approximation
- temporal difference
- neural network
- temporal difference learning
- temporal difference methods
- learning tasks
- reinforcement learning algorithms
- reinforcement learning problems
- model free
- policy search
- action space
- state space
- markov decision processes
- optimal policy
- markov decision problems
- learning process
- action selection
- machine learning
- artificial neural networks
- training set
- reinforcement learning methods
- multi agent