Oppositional extension of reinforcement learning techniques.
Masoud MahootchiHamid R. TizhooshKumaraswamy PonnambalamPublished in: Inf. Sci. (2014)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- state space
- reinforcement learning algorithms
- multiscale
- multi agent
- learning process
- markov decision processes
- learning problems
- learning algorithm
- dynamic programming
- real world
- optimal policy
- information systems
- optimal control
- computer vision
- transition model