Integrating sporadic imitation in Reinforcement Learning robots.
Willi RichertUlrich SchellerMarkus KochBernd KleinjohannClaudius SternPublished in: ADPRL (2009)
Keyphrases
- reinforcement learning
- imitation learning
- real robot
- mobile robot
- function approximation
- state space
- robot control
- robot behavior
- robotic control
- cooperative
- multi robot
- reinforcement learning algorithms
- human robot interaction
- reinforcement learning methods
- temporal difference learning
- model free
- markov decision processes
- optimal policy
- autonomous robots
- machine learning
- agent learns
- multi agent
- artificial agents
- supervised learning
- learning process
- multi robot systems
- learning algorithm
- policy search
- association rules
- multiple robots
- human robot
- markov decision process
- robotic systems
- temporal difference
- optimal control
- learning classifier systems