Curiosity-based topological reinforcement learning.
Muhammad Burhan HafezChu Kiong LooPublished in: SMC (2014)
Keyphrases
- reinforcement learning
- state space
- reinforcement learning algorithms
- markov decision processes
- function approximation
- temporal difference
- optimal policy
- topological properties
- machine learning
- direct policy search
- supervised learning
- learning algorithm
- connected components
- model free
- multi agent
- information systems
- markov chain
- learning process
- temporal difference learning
- topological features
- autonomous learning
- topology preservation
- geometric objects
- real world