Contributed Papers

Advancements in Reinforcement Learning and Decision Making

Mon, Aug 4, 2:00 PM - 3:50 PM Room CC-102A Music City Center

Yumeng WangChair

Section on Statistical Learning and Data Science

7 Presentations

Co-opetition in Online Seller Networks: Evidence from Etsy

2:05 PM - 2:20 PM

Co-authors: Burcu Eke Rubini (University of New Hampshire), Burcu Eke Rubini (University of New Hampshire), Ermira Zifla (University of New Hampshire)

egocentric network models additive and multiplicative effects models co-opetition online seller communities

Cooperation in Multi-Agent Reinforcement Learning with Proximal Policy Optimization

2:20 PM - 2:35 PM

Co-authors: Zsolt Talata (University of Kansas), Morteza Hashemi (University of Kansas), Zsolt Talata (University of Kansas), Amin Shojaeighadikolaei (University of Kansas)

reinforcement learning Markov decision process proximal policy optimization multi-agent cooperation electric power distribution networks

Empirical Bound Information-Directed Sampling for Norm-Agnostic Bandits

2:35 PM - 2:50 PM

Co-authors: Piotr Suder (Duke University), Piotr Suder (Duke University), Eric Laber

bandit algorithms heteroskedastic noise information-directed sampling parameter bounds

Low-Rank Online Dynamic Assortment with Dual Contextual Information

2:50 PM - 3:05 PM

Co-authors: Seong Jin Lee (University of North Carolina at Chapel Hill), Will Wei Sun (Purdue University), Seong Jin Lee (University of North Carolina at Chapel Hill), Yufeng Liu (University of North Carolina at Chapel Hill)

Bandit Algorithm Low-rankness Online Decision Making Reinforcement Learning

Offline Multi-Dimensional Distributional Reinforcement Learning: A Hilbert Space Embedding Approach

3:05 PM - 3:20 PM

Co-authors: Mehrdad Mohammadi (University of Illinois Urbana-Champaign), Qi Zheng (University of Louisville), Mehrdad Mohammadi (University of Illinois Urbana-Champaign), Ruoqing Zhu (University of Illinois Urbana-Champaign)

Reinforcement Learning Wasserstein Distance Reproducing Kernel Hilbert Space Non-parametric Matérn Kernel

Optimizing Navigation in Uncertain Terrain with Spatially Correlated Obstacles

3:20 PM - 3:35 PM

Co-authors: Li Zhou (Auburn University), Elvan Ceyhan (Auburn University), Li Zhou (Auburn University)

stochastic path planning sequential decision making Bayesian update distributional Reinforcement Learning network traversal Gaussian random fields

Semi-Parametric Batched Global Multi-Armed Bandits with Covariates

3:35 PM - 3:50 PM

Co-authors: Sakshi Arya (Case Western Reserve University), Sakshi Arya (Case Western Reserve University), Hyebin Song (Penn State)

multi-armed bandits semi-parametric single-index regression dynamic binning successive elimination regret bounds