Reinforcement Learning for Layout Planning - Modelling the Layout Problem as MDP.
Hendrik UngerFrank BörnerPublished in: APMS (3) (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- optimal policy
- state space
- markov decision process
- learning algorithm
- dynamic programming
- function approximation
- planning problems
- layout design
- markov decision problems
- partially observable
- heuristic search
- action selection
- reinforcement learning algorithms
- linear programming
- reinforcement learning problems
- machine learning
- model free
- domain independent
- average reward
- learning process
- graph layout