RLayout: Interior Design System Based on Reinforcement Learning.
Ningqi WangChang NiuZizhong LiPublished in: ISCID (1) (2019)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- learning process
- markov decision processes
- robotic control
- control problems
- learning algorithm
- multi agent
- data sets
- temporal difference
- optimal control
- transfer learning
- state space
- optimal policy
- dynamic programming
- temporal difference learning
- search space
- expert systems
- model free
- information retrieval
- learning agents
- partially observable domains
- function approximators
- direct policy search
- partially observable
- supervised learning
- hidden markov models
- artificial intelligence
- genetic algorithm
- machine learning