Research map / Bandits and online learning / Multi-armed bandits
Incorporating Behavioral Constraints in Online AI Systems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Set blend=0.25 to combine the learned constraints with online reward | BCTS · Warfarin | behavioral errors: 1,500 versus nearly 20,000 | Helped |
| Use random sampling rather than CTS to collect constraint-training examples (ablation) | BCTS · MovieLens | behavioral errors: E(T)=0 | Helped |
| Use random sampling rather than CTS to collect constraint-training examples (ablation) | BCTS · MovieLens | regret | Helped |
| Increase sensitivity to online reward using blend=1.0 (ablation) | BCTS · Warfarin | regret | Helped |
| Increase sensitivity to online reward using blend=1.0 (ablation) | BCTS · Warfarin | behavioral errors: nearly 20,000 | Hurt |
| Use blend=0.25 rather than relying only on reward feedback (ablation) | BCTS · MovieLens | behavioral errors | Helped |
Closest papers by meaning
- Contextual Bandits and Imitation Learning with Preference-Based Active Queries (NeurIPS 2023 · similarity 0.88)
- Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints (ICML 2024 · similarity 0.88)
- Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations (NeurIPS 2023 · similarity 0.88)
- Learning Human Objectives by Evaluating Hypothetical Behavior (ICML 2020 · similarity 0.87)
- Behavioral Exploration: Learning to Explore via In-Context Adaptation (ICML 2025 · similarity 0.87)
- Provably Efficient Exploration in Inverse Constrained Reinforcement Learning (ICML 2025 · similarity 0.85)
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.