Research map / Multi-agent systems and games / Games and equilibria
Matching multiple experts: on the exploitability of multi-agent imitation learning
Antoine Bergerault, Volkan Cevher, Negar Mehr
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 |
|---|---|---|---|
| assume a dominant strategy equilibrium expert (delta-continuity with delta=0) | behavioral cloning in n-player Markov games · theory: Nash gap bound | Nash gap bound | Improved |
| exactly match expert occupancy measures without full-state support | multi-agent imitation learning · theory: Nash gap | exploitability | Hurt |
| increase BC error in Tag-Game (ablation) | perturbed expert policies · Tag-Game (gamma=0.8) | Nash gap and delta | Hurt |
Closest papers by meaning
- Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning (NeurIPS 2025 · similarity 0.93)
- Multi-Agent Imitation Learning: Value is Easy, Regret is Hard (NeurIPS 2024 · similarity 0.91)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.90)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · similarity 0.89)
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation (NeurIPS 2026 · similarity 0.88)
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.
