Fast Reinforcement Learning under Uncertainties with Self-Organizing Neural Networks.
Teck-Hou TengAh-Hwee TanPublished in: WI-IAT (2) (2015)
Keyphrases
- reinforcement learning
- state space
- learning algorithm
- function approximation
- markov decision processes
- reinforcement learning algorithms
- machine learning
- temporal difference
- database
- transfer learning
- direct policy search
- multi agent reinforcement learning
- continuous state
- control problems
- optimal control
- expert systems
- multi agent
- optimal policy
- dynamic programming
- search space
- robot control
- real world
- databases
- policy search
- robotic control
- real time