Sequential Decision Making

Sequential decision-making (SDM) focuses on optimizing a series of actions over time to achieve a desired outcome in uncertain environments. Current research emphasizes developing efficient algorithms, often based on reinforcement learning (RL) or Bayesian methods, to handle complex scenarios with multiple objectives, delayed feedback, and high-dimensional data, incorporating techniques like Thompson sampling, Monte Carlo Tree Search, and various neural network architectures. SDM's significance lies in its broad applicability across diverse fields, from personalized medicine and financial modeling to robotics and resource management, driving advancements in both theoretical understanding and practical problem-solving.

Papers

September 29, 2022

Blessing from Human-AI Interaction: Super Reinforcement Learning in Confounded Environments
Jiayi Wang, Zhengling Qi, Chengchun Shi
Policy Learning Human AI Interaction Sequential Decision Making Blessing Generation Super Learner

September 8, 2022

Sequential Information Design: Learning to Persuade in the Dark
Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovo
Bandit Feedback O$ Regret Sequential Decision Making Persuasive Argument Persuasive Capability Efficient Realization Sequential Information Design

August 17, 2022

Sampling Through the Lens of Sequential Decision Making
Jason Xiaotian Dou, Alvin Qingkai Pan, Runxue Bao, Haiyi Harry Mao, Lei Luo, Zhi-Hong Mao
Reinforcement Learning Camera Lens Sequential Decision Making Data Sampling

July 12, 2022

Contextual Bandits with Large Action Spaces: Made Practical
Yinglun Zhu, Dylan J. Foster, John Langford, Paul Mineiro
Action Space Contextual Bandit Sequential Decision Making Contextual Bandit Problem

June 27, 2022

Utility Theory for Sequential Decision Making
Mehran Shakerinava, Siamak Ravanbakhsh
Reinforcement Learning Markov Decision Process Sequential Decision Sequential Decision Making Utility Based Markov Reward Process

May 30, 2022

Causal Explanations for Sequential Decision Making Under Uncertainty
Samer B. Nashed, Saaduddin Mahmud, Claudia V. Goldman, Shlomo Zilberstein
Markov Decision Process Causal Inference High Uncertainty Anticipation Structural Causal Model Sequential Decision Making Causal Explanation

April 28, 2022

Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers
Micah Carroll, Jessy Lin, Orr Paradise, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin
Language Model Behavior Cloning Sequential Decision Making Problem Sequential Decision Making Bidirectional Transformer Flexible Inference Mask Sequence

April 4, 2022

Achieving Long-Term Fairness in Sequential Decision Making
Yaowei Hu, Lu Zhang
Procedural Fairness Causal Graph Sequential Decision Making Long Term Fairness Term Fairness

March 23, 2022

NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty
Jonathan Balloch, Zhiyu Lin, Mustafa Hussain, Aarun Srinivas, Robert Wright, Xiangyu Peng, Julia Kim, Mark Riedl
Reinforcement Learning Sequential Decision Making Novelty Search Novel Reinforcement Learning Agent Evaluation Grid World Novelty Generation

November 28, 2021

Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation
Ramtin Keramati, Omer Gottesman, Leo Anthony Celi, Finale Doshi-Velez, Emma Brunskill
Person Identification Policy Evaluation Complementary Benefit Heterogeneous Treatment Effect Sequential Decision Making Subgroup Description Decision Policy Individual Prediction

December 8, 2011

The Extended UCB Policies for Frequentist Multi-armed Bandit Problems
Keqin Liu, Tianshuo Zheng, Haoran Chen
Multi Armed Bandit Robust Policy Sequential Decision Making UCB Algorithm Heavy Tailed Reward