Reinforcement learning of sensor-based reaching strategies for a two-link manipulator.
Pedro MartínJosé del R. MillánPublished in: IROS (1996)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- state space
- degrees of freedom
- model free
- control method
- learning process
- optimal control
- control system
- learning problems
- vision system
- multi agent reinforcement learning
- control strategies
- link structure
- path planning
- real time
- computer vision
- social networks
- genetic algorithm
- machine learning
- neural network