73 citations
- Baylor UniversityUS7 papers
- Brandon UniversityCA2 papers
- California Institute of TechnologyUS2 papers
- Princeton UniversityUS2 papers
- Rochester Institute of TechnologyUS2 papers
- Argonne National LaboratoryUS1 paper
- Carnegie Mellon UniversityUS1 paper
- Columbia UniversityUS1 paper
- Dominion Astrophysical ObservatoryCA1 paper
- European Southern ObservatoryCL1 paper
- FZU ‒ Institute of Physics of the Academy of Sciences of the Czech RepublicCZ1 paper
- Georgia Institute of TechnologyUS1 paper
Showing 2017Show all
3 papers · 1 filter
cs.AI2017★ 14 cited
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
Zachary Lipton, Xiujun Li, Jianfeng Gao +3
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawi…
math.CO2017
Extrema Property of the -Ranking of Directed Paths and Cycles
Breeanne Baker Swart, Rigoberto Flórez, Darren A. Narayan +1
A -ranking of a directed graph is a labeling of the vertex set of with positive integers such that every directed path connecting two vertices with the same label in…
math.CO2017
Maximizing the number of edges in optimal -rankings
Rigoberto Florez, Darren A. Narayan
A -ranking is a vertex -coloring such that if two vertices have the same color any path connecting them contains a vertex of larger color. The rank number of a graph is small…