Tagged articles

Sequential Decision-Making

3 articles · Page 1 of 1

Aug 10, 2026 · Artificial Intelligence

Bayesian Ensemble (BE): Adaptive Ensemble Selection for Bandits and Reinforcement Learning

The paper introduces Bayesian Ensemble (BE), a lightweight Bayesian layer that dynamically updates the sampling distribution over ensemble members using observed rewards, and extends it to Bayesian Ensemble Bandit (BEB) and Bayesian Ensemble DQN (BE‑DQN), achieving significant regret and click‑through improvements across synthetic, real‑world, and RL benchmarks with minimal computational overhead.

BanditBayesian EnsembleEnsemble Methods

0 likes · 12 min read

Bayesian Ensemble (BE): Adaptive Ensemble Selection for Bandits and Reinforcement Learning

DataFunSummit

Mar 5, 2023 · Artificial Intelligence

Data‑Driven Decision Optimization: Challenges and Advances in Offline Reinforcement Learning

This article reviews the practical challenges of applying data‑driven decision optimization in real‑world systems, explains the fundamentals of offline reinforcement learning, discusses recent algorithmic innovations such as policy‑constraint methods and the DOGE framework, and presents industrial case studies including power‑plant control and mixed offline‑online RL approaches.

Sequential Decision-Makingdata‑driven decisionindustrial AI

0 likes · 27 min read

Data‑Driven Decision Optimization: Challenges and Advances in Offline Reinforcement Learning

Architects Research Society

Oct 4, 2015 · Artificial Intelligence

Bayesian Thinking on Your Feet: Embedding Generative Models in Reinforcement Learning for Sequentially Revealed Data

This NSF‑funded project aims to develop algorithms that incrementally process partially observed data, integrating generative models with reinforcement‑learning policies to decide when to act, applied to simultaneous machine translation and quiz‑bowl style question answering.

Generative ModelsSequential Decision-Makingbayesian inference

0 likes · 4 min read

Bayesian Thinking on Your Feet: Embedding Generative Models in Reinforcement Learning for Sequentially Revealed Data