Improving the Robustness of Instance-Based Reinforcement Learning Robots by Metalearning.
Toshiyuki YasudaKousuke ArakiKazuhiro OhkuraPublished in: J. Adv. Comput. Intell. Intell. Informatics (2011)
Keyphrases
- reinforcement learning
- robot control
- robotic control
- mobile robot
- multi robot
- cooperative
- real robot
- knn
- function approximation
- meta learning
- state space
- instance based learning
- action selection
- machine learning
- markov decision processes
- robotic systems
- reinforcement learning algorithms
- multi agent reinforcement learning
- artificial agents
- transition model
- robotic agents
- learning process
- multi agent systems
- multi agent
- multi robot systems
- robot behavior
- formation control
- data sets
- evolutionary learning
- lego mindstorms
- robot soccer
- data mining problems
- human robot interaction
- autonomous robots
- computational efficiency
- multistage
- optimal policy
- supervised learning
- decision trees
- learning algorithm