Efficient learning of reactive robot behaviors with a Neural-Q_learning approach.
Marc CarrerasPere RidaoJoan BatlleTudor NicoseviciPublished in: IROS (2002)
Keyphrases
- efficient learning
- real robot
- evolutionary robotics
- mobile robot
- reinforcement learning
- learning algorithm
- potential field
- unknown environments
- sensory inputs
- neural network
- human robot interaction
- network architecture
- multi agent
- sensory motor
- multi robot
- path planning
- robotic systems
- autonomous robots
- robot navigation
- cooperative
- biologically inspired
- function approximation
- central pattern generator
- agent architecture
- state space
- pattern languages
- obstacle avoidance
- humanoid robot
- motor control
- dynamic environments
- log linear models
- vision system
- database systems
- artificial intelligence