Parallel Online Temporal Difference Learning for Motor Control.
Wouter CaarlsErik SchuitemaPublished in: IEEE Trans. Neural Networks Learn. Syst. (2016)
Keyphrases
- temporal difference learning
- motor control
- function approximation
- fixed point
- evaluation function
- game playing
- temporal difference
- online learning
- reinforcement learning
- mobile robot
- biologically inspired
- humanoid robot
- reinforcement learning algorithms
- robot control
- markov decision process
- genetic algorithm
- function approximators
- data mining
- radial basis function
- learning activities
- state space