Decomposition methods with deep corrections for reinforcement learning. Bouton, M., Julian, K. D., Nakhaei, A., Fujimura, K., & Kochenderfer, M. J. Autonomous Agents and Multi-Agent Systems, 33(3):330–352, 2019.
Decomposition methods with deep corrections for reinforcement learning [link]Paper  doi  bibtex   

Downloads: 0