Neural reinforcement learning for behaviour synthesis.
Claude F. TouzetPublished in: Robotics Auton. Syst. (1997)
Keyphrases
- reinforcement learning
- fitted q iteration
- network architecture
- neural network
- function approximation
- reward function
- controller synthesis
- learning algorithm
- bio inspired
- reinforcement learning algorithms
- multi agent
- optimal policy
- state space
- neural computation
- user behaviour
- machine learning
- learning rules
- data sets
- biologically plausible
- program synthesis
- neural information processing
- biologically inspired
- closed loop
- stochastic approximation
- search algorithm
- dynamic programming
- least squares
- computational intelligence
- policy search
- artificial neural
- hebbian learning
- transfer learning
- learning classifier systems
- sensory inputs
- associative memory
- neural model
- optimal control
- temporal difference