Generating 2D Lego Compatible Puzzles Using Reinforcement Learning.
Cheolseong ParkHeekyung YangKyungha MinPublished in: IEEE Access (2020)
Keyphrases
- reinforcement learning
- optimal policy
- robotic control
- learning process
- databases
- multi agent
- real time
- policy search
- state space
- machine learning
- temporal difference learning
- constraint satisfaction
- function approximation
- model free
- reinforcement learning algorithms
- evaluation function
- stochastic approximation
- control problems
- markov decision processes
- control system
- information retrieval
- artificial neural networks