( events)   Timezone: »  
Tue Dec 14 10:50 AM -- 07:30 PM (PST)
Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice
Aurelien Bibaut · Maria Dimakopoulou · Nathan Kallus · Xinkun Nie · Masatoshi Uehara · Kelly Zhang

Sequential decision-making problems appear in settings as varied as healthcare, e-commerce, operations management, and policymaking, and depending on the context these can have very varied features that make each problem unique. Problems can involve online learning or offline data, known cost structures or unknown counterfactuals, continuous actions with or without constraints or finite or combinatorial actions, stationary environments or environments with dynamic agents, utilitarian considerations or fairness or equity considerations. More and more, causal inference and discovery and adjacent statistical theories have come to bear on such problems, from the early work on longitudinal causal inference from the last millenium up to recent developments in bandit algorithms and inference, dynamic treatment regimes, both online and offline reinforcement learning, interventions in general causal graphs and discovery thereof, and more. While the interaction between these theories has grown, expertise is spread across many different disciplines, including CS/ML, (bio)statistics, econometrics, ethics/law, and operations research.

The primary purpose of this workshop is to convene both experts, practitioners, and interested young researchers from a wide range of backgrounds to discuss recent developments around causal inference in sequential decision making and the avenues forward on the topic, especially ones that bring together ideas from different fields. The all-virtual nature of this year's NeurIPS workshop makes it particularly felicitous to such an assembly. The workshop will combine invited talks and panels by a diverse group of researchers and practitioners from both academia and industry together with contributed talks and town-hall Q\&A that will particularly seek to draw from younger individuals new to the area.

Opening Remarks
TBD (Elias Bareibnboim) (Live Talk and Q&A)
Sequential Adaptive Designs for Learning Optimal Individualized Treatment Rules with Formal Inference (Mark van der Laan) (Live Talk and Q&A)
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting (Claire Vernade) (Live Talk and Q&A)
Panel Discussion (Discussion Panel)
Poster Presentation
Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning (Guy Tennenholtz) (Oral Presentation)
MAGNET: Multi-Agent Graph Cooperative Bandits (Hengrui Cai) (Oral Presentation)
(un)fairness in sequential decision making as a challenge (Razieh Nabi) (Live Talk and Q&A)
Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process (Rui Song) (Live Talk and Q&A)
TALK (Susan Athey) (Live Talk and Q&A)
Panel Discussion
What Would the Expert $do(\cdot)$?: Causal Imitation Learning (Gokul Swamy) (Oral Presentation)
The Limits to Learning a Diffusion Model (Andy Zheng) (Oral Presentation)
Deviation-Based Learning (Komiyama Junpei) (Oral Presentation)
Closing Remarks (Remarks)
Poster Presentation
Doubly robust confidence sequences (Poster)
Kernel Methods for Multistage Causal Inference: Mediation Analysis and Dynamic Treatment Effects (Poster)
Deviation-Based Learning (Poster)
MAGNET: Multi-Agent Graph Cooperative Bandits (Poster)
Understanding User Podcast Consumption Using Sequential Treatment Effect Estimation (Poster)
Deviation-Based Learning (Oral)
Chronological Causal Bandit (Poster)
Estimating the Long-Term Effects of Novel Treatments (Poster)
Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning (Oral)
What Would the Expert $do(\cdot)$?: Causal Imitation Learning (Poster)
Double/Debiased Machine Learning for Dynamic Treatment Effects via $g$-Estimation (Poster)
A Validation Tool for Designing Reinforcement Learning Environments (Poster)
Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization (Poster)
Reinforcement Learning in Reward-Mixing MDPs (Poster)
The Limits to Learning a Diffusion Model (Poster)
On Adaptivity and Confounding in Contextual Bandit Experiments (Poster)
Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning (Poster)
A Causality-based Graphical Test to obtain an Optimal Blocking Set for Randomized Experiments (Poster)
Beyond Ads: Sequential Decision-Making Algorithmsin Public Policy (Poster)
Practical Policy Optimization with PersonalizedExperimentation (Poster)
Multiple imputation via state space model for missing data in non-stationary multivariate time series (Poster)
Learning Treatment Effects in Panels with General Intervention Patterns (Poster)
Bandits with Partially Observable Confounded Data (Poster)
A Variational Information Bottleneck Principle for Recurrent Neural Networks (Poster)
What Would the Expert $do(\cdot)$?: Causal Imitation Learning (Oral)
Off-Policy Evaluation with Embedded Spaces (Poster)
Partition-based Local Independence Discovery (Poster)
The Limits to Learning a Diffusion Model (Oral)
MAGNET: Multi-Agent Graph Cooperative Bandits (Oral)
Causal Multi-Agent Reinforcement Learning: Review and Open Problems (Poster)
Dynamic Causal Discovery in Imitation Learning (Poster)