Approximating the value function for continuous space reinforcement learning in robot control.
Sebastian BuckMichael BeetzThorsten SchmittPublished in: IROS (2002)
Keyphrases
- robot control
- continuous space
- reinforcement learning
- mobile robot
- autonomous robots
- discrete space
- function approximation
- mathematical morphology
- function approximators
- subsumption architecture
- machine learning
- pid controller
- global optimization
- similarity search
- gray scale
- image segmentation
- image processing
- learning algorithm