Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces. Bester, C. J., James, S. D., & Konidaris, G. D. arXiv:1905.04388 [cs, stat], May, 2019. arXiv: 1905.04388
Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces [link]Paper  bibtex   

Downloads: 0