Research map / Bandits and online learning / Online convex optimization and games
No-Regret Learning in Dynamic Competition with Reference Effects Under Logit Demand
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 |
|---|---|---|---|
| use diminishing step-sizes satisfying the stated conditions | OPGA · Dynamic duopoly with MNL demand and reference effects | convergence to SNE | Helped |
| choose step-sizes η^t = Θ(1/t) | OPGA · Dynamic duopoly with MNL demand and reference effects | squared price and reference-price error rate: O(1/t) | Helped |
| use the over-large constant step-size η^t = 1 instead of diminishing step-sizes (ablation) | OPGA · Example 2 | price and reference-price convergence | Hurt |
| use diminishing step-sizes instead of the over-large constant step-size η^t = 1 (ablation) | OPGA · Examples 1 and 2 | price and reference-price convergence | Helped |
| use OPGA rather than repeatedly applying the equilibrium pricing policy | Dynamic duopoly with reference effects · Example 3 | rate of reaching SNE | No clear effect |
Closest papers by meaning
- No-regret Learning in Price Competitions under Consumer Reference Effects (NeurIPS 2020 · similarity 0.93)
- Revenue Maximization Under Sequential Price Competition Via The Estimation Of $s$-Concave Demand Functions (ICLR 2026 · similarity 0.89)
- Beyond Monotonicity: On the Convergence of Learning Algorithms in Standard Auction Games (AAAI 2025 · similarity 0.88)
- Decentralized and Uncoordinated Learning of Stable Matchings: A Game-Theoretic Approach (AAAI 2025 · similarity 0.88)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.87)
- Improved Bandits in Many-to-One Matching Markets with Incentive Compatibility (AAAI 2024 · 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.