Research map / Multi-agent systems and games / Games and equilibria
Emergent Reciprocity and Team Formation from Randomized Uncertain Social Preferences
Bowen Baker
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 |
|---|---|---|---|
| train with randomized uncertain social preferences instead of selfish rewards | MARL agents · Iterated Prisoner's Dilemma self-play | defect actions | Improved |
| raise maximum uncertainty sigma_max (ablation) | RUSP agents · Iterated Prisoner's Dilemma | cooperation | Improved |
| set uncertainty to zero (sigma_max = 0) (ablation) | RUSP agents · Indirect reciprocity IPD, Hold Out | defection against fixed agent | Hurt |
| add RUSP to 3-player Oasis game | MARL agents · Oasis | mean reward and deaths | Improved |
| non-zero uncertainty over relationships versus certain baseline (ablation) | RUSP agents · Oasis | team formation | Improved |
| replace asymmetric independent uncertainty with symmetric noise (ablation) | RUSP · Iterated Prisoner's Dilemma | reciprocity | Hurt |
| remove past policy play (10% of agents use past policy versions) (ablation) | RUSP agents · Iterated Prisoner's Dilemma | reciprocity stability | Hurt |
| sample integer partitions instead of full matrix randomization (ablation) | RUSP reward transformation · Prisoner's Buddy | team choice | No clear effect |
| add uncertainty | RUSP agents · Harvest and Cleanup public goods | collective return | No clear effect |
Closest papers by meaning
- Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents (NeurIPS 2024 · similarity 0.89)
- A Unified Model of Direct and Indirect Reciprocity in Multichannel Games (AAAI 2025 · similarity 0.88)
- Training Generalizable Collaborative Agents via Strategic Risk Aversion (NeurIPS 2026 · similarity 0.87)
- Online Learning of Coalition Structures by Selfish Agents (AAAI 2025 · similarity 0.87)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.86)
- Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games (NeurIPS 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.
