Improving Reinforcement Learning Control Via Online Bilinear Action Interpolation.
Carlos H. C. RibeiroElder Moreira HemerlyPublished in: SBRN (1998)
Keyphrases
- reinforcement learning
- action selection
- control problems
- optimal control
- online learning
- multi agent
- action space
- robot control
- control system
- real time
- state action
- function approximation
- partially observable domains
- robotic control
- image interpolation
- temporal difference
- adaptive control
- control strategy
- optimal policy
- state space
- learning process
- machine learning