Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Learning to Interact With Learning Agents
Adish Singla, Hamed Hassani, Andreas Krause
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use LIL forecaster instead of EXP3 under adversarial losses | EXP3 · Two experts, adversarial losses (Fig 1a) | regret | Improved |
| Use LIL instead of EXP3 under stochastic losses | EXP3 · Two experts, stochastic losses | regret slope: 0.47 -> 0.56 | Hurt |
| Give all experts feedback (ALL-LEARN) instead of LIL | LIL · Two experts, stochastic losses | regret slope: 0.56 -> 0.40 | Improved |
| Switch LIL from adversarial to stochastic losses | LIL · Two experts | regret | No clear effect |
Closest papers by meaning
- Bayesian Decision Making around Experts (NeurIPS 2026 · similarity 0.88)
- Managing Self-Learning Experts under Per-Round Budget Constraints (NeurIPS 2026 · similarity 0.87)
- Bandits with Abstention under Expert Advice (NeurIPS 2024 · similarity 0.87)
- Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making (NeurIPS 2025 · similarity 0.86)
- Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback (NeurIPS 2026 · similarity 0.86)
- Learning to Recommend in Unknown Games (NeurIPS 2026 · similarity 0.86)
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.
