Research map / Multi-agent systems and games / Games and equilibria
Learning Strategic Network Emergence Games
Rakshit Trivedi, Hongyuan Zha
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 |
|---|---|---|---|
| Transfer learned reward to larger network instead of training from scratch | MINE · Andorra | Correct links (%): 76.5 -> 70.2 | Hurt |
| Transfer learned reward to larger Andorra network | MINE · Andorra | Training episodes: 100000 -> 72000 | Improved |
| Transfer reward across player sets in Trade network | MINE · Trade | Correct links (%): 87.2 -> 81 | Hurt |
| Transfer reward across player sets in Trade network | MINE · Trade | Training episodes: 25000 -> 18000 | Improved |
| Transfer reward across player sets in Movie bipartite network | MINE · Movie | Correct links (%): 62.54 -> 53.09 | Hurt |
| Transfer reward in Movie network | MINE · Movie | Training episodes: 60000 -> 45000 | Improved |
| Direct policy transfer without retraining instead of re-optimizing policy on transferred reward | MINE · Trade | Correct links (%): 81 -> 62.45 | Hurt |
| Direct policy transfer without retraining instead of re-optimizing policy | MINE · Andorra | Correct links (%): 70.2 -> 68.88 | Hurt |
| Direct policy transfer without retraining instead of re-optimizing policy | MINE · Movie | Correct links (%): 53.09 -> 51.1 | Hurt |
| Evaluate under perturbed graph (leaders swapped with followers) instead of policy-generated graph (ablation) | MINE · Karate club, Leader#Red | Expected return under learned payoff: -141.71 -> -221.4 | Hurt |
| Evaluate under perturbed graph instead of policy-generated graph (ablation) | MINE · Karate club, Community#Purple | Expected return under learned payoff: -77.04 -> -101.65 | Hurt |
| Compare MINE with Social Game Embed on link prediction | MINE · Arxiv GR-QC | AUC: 0.855 vs 0.857 | Mixed |
Closest papers by meaning
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.88)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.87)
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma (ICML 2025 · similarity 0.85)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.85)
- Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning (ICML 2024 · similarity 0.85)
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.
