Mastering construction heuristics with self-play deep reinforcement learning.
Qi WangYuqing HeChunlei TangPublished in: Neural Comput. Appl. (2023)
Keyphrases
- reinforcement learning
- control strategies
- machine learning
- robotic control
- function approximation
- search strategies
- dynamic programming
- multi agent
- database
- hidden markov models
- state space
- heuristic search
- transfer learning
- markov decision processes
- learning process
- heuristic methods
- genetic algorithm
- action selection
- temporal difference
- reinforcement learning algorithms
- markov decision process