Research map / Bandits and online learning / Online convex optimization and games
Online Decision-Focused Learning under Semi-Bandit Feedback
Aabhash Dhakal, Tim Lachner, Jayanta Mandi, Marco Foschini, Christoph M Flath
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies decision-focused learning in an online setting where the agent observes costs only for selected actions (semi-bandit feedback), rather than full cost vectors.
Problem
Decision-focused learning typically assumes offline full-feedback data with complete cost vectors, whereas many real-world decision systems operate online and observe costs only for the actions they select.
Approach
Extends decision-focused learning to online semi-bandit feedback, where predictive models are trained to minimize decision regret using only partial cost observations from past rounds. Details beyond the abstract are not available.
Experimental setup
Metrics: decision regret
Builds on: decision-focused learning predict-then-optimize
Closest papers by meaning
- DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback (ICLR 2025 · similarity 0.88)
- Decision-Focused Learning with Directional Gradients (NeurIPS 2024 · similarity 0.88)
- Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approach (AAAI 2024 · similarity 0.88)
- Diffusion Models Meet Contextual Bandits (NeurIPS 2025 · similarity 0.88)
- Solver-Free Decision-Focused Learning for Linear Optimization Problems (NeurIPS 2025 · similarity 0.88)
- DFF: Decision-Focused Fine-Tuning for Smarter Predict-Then-Optimize with Limited Data (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
