Research map / Bandits and online learning / Online convex optimization and games
Learning to Play Sequential Games versus Unknown Opponents
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 StackelUCB with kernel-based response modeling and optimistic rewards | Traffic routing on the Sioux-Falls network · Traffic routing | regret | Helped |
| Use StackelUCB instead of routing all units via the shortest route or routing no units | Traffic routing on the Sioux-Falls network · Traffic routing | cumulative reward | Helped |
| Choose alternative routes based on users' demands using StackelUCB | Traffic routing on the Sioux-Falls network · Traffic routing | average congestion | Helped |
| Learn the opponent's response function and exploit the bilevel reward structure | Wildlife patrol strategy · Wildlife conservation | reward | Helped |
| Model the poacher response and optimize the bilevel reward rather than learning the overall objective directly (ablation) | StackelUCB versus GP-UCB · Wildlife conservation | convergence to optimal strategy: ∼60 | Helped |
| Use StackelUCB instead of the full-information Hedge algorithm | Traffic routing on the Sioux-Falls network · Traffic routing | regret | No clear effect |
Closest papers by meaning
- Learning to Steer Learners in Games (ICML 2025 · similarity 0.89)
- Regret Minimization in Stackelberg Games with Side Information (NeurIPS 2024 · similarity 0.89)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.88)
- Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms (NeurIPS 2024 · similarity 0.87)
- An Open-Ended Learning Framework for Opponent Modeling (AAAI 2025 · similarity 0.87)
- Opponent Modeling based on Subgoal Inference (NeurIPS 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.