Login / Signup
Generative inverse reinforcement learning for learning 2-opt heuristics without extrinsic rewards in routing problems.
Qi Wang
Yongsheng Hao
Jiawei Zhang
Published in:
J. King Saud Univ. Comput. Inf. Sci. (2023)
Keyphrases
</>
inverse reinforcement learning
reinforcement learning
routing problem
unsupervised learning
supervised learning
search algorithm
machine learning
learning algorithm
heuristic search
learning tasks
partially observable environments