Towards Concurrent Q-Learning on Linked Multi-Component Robotic Systems.
Borja Fernández-GaunaJosé Manuel López-GuedeManuel GrañaPublished in: HAIS (2) (2011)
Keyphrases
- robotic systems
- multi component
- hierarchical reinforcement learning
- reinforcement learning
- function approximation
- cooperative
- mobile robot
- control architecture
- vision system
- real robot
- state space
- multi agent
- learning algorithm
- indoor environments
- multi robot
- autonomous robots
- model free
- non stationary
- optimal policy
- robotic tasks
- reinforcement learning algorithms
- action selection
- computer vision
- unstructured environments
- learning rate
- stochastic approximation
- robotic manipulator
- object manipulation
- learning agent
- manipulation tasks
- real time