Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs. Low, S., Kumar, A., & Sanner, S. In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-22), Online, 2022.
Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs [pdf]Paper  bibtex   6 downloads  

Downloads: 6