Research map / Multi-agent systems and games / Games and equilibria
Multi-agent imitation learning with function approximation: linear Markov games and beyond
Luca Viano, Till Freihaut, Emanuele Nevali, Volkan Cevher, Matthieu Geist, Giorgia Ramponi
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 |
|---|---|---|---|
| replace BC with DQN-Explore-BC | Deep MAIL · Connect4 win rate vs solver noise 3 | win rate: 0.21 -> 0.81 | Improved |
| replace BC with DQN-Explore-BC | Deep MAIL · Connect4 win rate vs approx. best response | win rate: 0.00 -> 0.21 | Improved |
| replace Deep BC with DQN-Explore-BC | Deep MAIL · Tic-Tac-Toe | Nash gap | Improved |
| use interactive LSVI-UCB-ZERO-BC instead of BC | Gridworld linear MAIL, tabular features · 3x3 zero-sum Gridworld | Nash gap | Improved |
| use relational features (d=80) instead of tabular (d=288) | LSVI-UCB-ZERO-BC · 3x3 zero-sum Gridworld | Nash gap convergence | Improved |
| use relational features instead of tabular features | BC · 3x3 zero-sum Gridworld | Nash gap | No clear effect |
| use deep linear network features (d=262) instead of tabular | BC · 3x3 zero-sum Gridworld | Nash gap | Improved |
Closest papers by meaning
- Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning (NeurIPS 2025 · similarity 0.89)
- Multi-Agent Imitation Learning: Value is Easy, Regret is Hard (NeurIPS 2024 · similarity 0.89)
- Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning (NeurIPS 2024 · similarity 0.88)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.88)
- MisoDICE: Multi-Agent Imitation from Mixed-Quality Demonstrations (NeurIPS 2025 · similarity 0.87)
- Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms (ICML 2024 · 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.
