Research map / Multi-agent systems and games / Games and equilibria
Robust Multi-agent Counterfactual Prediction
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 |
|---|---|---|---|
| allow small positive ε-equilibrium regret | RMAC auction revenue predictions · 2-player auctions | revenue bounds | Mixed |
| use RMAC bounds instead of a point estimate when types are not identified | RMAC · Second-price auction with reserve .5 | counterfactual revenue bounds | Mixed |
| change the mechanism from Boston to RSD | RMAC · School choice | truthfulness | Mixed |
| change the mechanism from Boston to RSD | RMAC · School choice | social welfare | Mixed |
| change the mechanism from RSD to Boston | RMAC · School choice with identical student preferences | truthfulness | Hurt |
| change the mechanism from RSD to Boston | RMAC · School choice with identical student preferences | social welfare | No clear effect |
| use the mean mechanism, where a range of types can report extreme actions in equilibrium | RMAC · Social choice | type identification | Hurt |
| use a small nonzero ε in the mean mechanism | RMAC · Social choice | solution uniqueness | Helped |
| use the median mechanism rather than VCG | RMAC · Social choice | robustness to reporting deviations | Mixed |
Closest papers by meaning
- Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making (ICML 2025 · similarity 0.86)
- Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamics (NeurIPS 2025 · similarity 0.84)
- Decoding Rewards in Competitive Games: Inverse Game Theory with Entropy Regularization (ICML 2025 · similarity 0.84)
- Generating Likely Counterfactuals Using Sum-Product Networks (ICLR 2025 · similarity 0.84)
- Counterfactual Realizability (ICLR 2025 · similarity 0.84)
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning (NeurIPS 2025 · similarity 0.84)
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.