Towards Direct Policy Search Reinforcement Learning for Robot Control.
Andres El-FakdiMarc CarrerasPere RidaoPublished in: IROS (2006)
Keyphrases
- robot control
- direct policy search
- reinforcement learning
- mountain car
- state space
- function approximation
- reinforcement learning algorithms
- mobile robot
- machine learning
- learning algorithm
- model free
- temporal difference
- markov decision processes
- subsumption architecture
- transfer learning
- control problems
- evolutionary algorithm
- control strategies
- learning process
- markov decision process
- pid controller
- dynamic model
- fuzzy sets