Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics. Weissenbacher, M., Sinha, S., Garg, A., & Kawahara, Y. June, 2022. arXiv:2111.01365 [cs]
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics [link]Paper  doi  bibtex   

Downloads: 0