# Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas

arXiv: https://arxiv.org/abs/2601.22292 · HTML: https://mlsanity.com/paper/2601.22292/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 22 of 22)

- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (2017)
- [Open Problems in Cooperative AI](https://mlsanity.com/paper/2012.08630/) (2020)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Inequity aversion improves cooperation in intertemporal social dilemmas](https://mlsanity.com/paper/1803.08884/) (2018)
- [A multi-agent reinforcement learning model of common-pool resource appropriation](https://mlsanity.com/paper/1707.06600/) (2017)
- [Learning to Incentivize Other Learning Agents](https://mlsanity.com/paper/2006.06051/) (2020)
- [Melting Pot 2.0](https://mlsanity.com/paper/2211.13746/) (2022)
- [Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma](https://mlsanity.com/paper/2501.16173/) (2025)
- [A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings](https://mlsanity.com/paper/2106.09012/) (2021)
- [Towards Theoretical Understanding of Inverse Reinforcement Learning](https://mlsanity.com/paper/2304.12966/) (2023)
- [Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas](https://mlsanity.com/paper/2402.17270/) (2024)
- [Cooperative Resilience in Artificial Intelligence Multiagent Systems](https://mlsanity.com/paper/2409.13187/) (2024)
- [Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality](https://mlsanity.com/paper/2210.01380/) (2022)
- [The social dilemma in artificial intelligence development and why we have to solve it](https://mlsanity.com/paper/2107.12977/) (2021)
- [Explaining Decisions of Agents in Mixed-Motive Games](https://mlsanity.com/paper/2407.15255/) (2024)
- [Efficient Inverse Multiagent Learning](https://mlsanity.com/paper/2502.14160/) (2025)
- [Collaboration Promotes Group Resilience in Multi-Agent RL](https://mlsanity.com/paper/2111.06614/) (2021)
- [Understanding the World to Solve Social Dilemmas Using Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2305.11358/) (2023)
- [Inverse Concave-Utility Reinforcement Learning is Inverse Game Theory](https://mlsanity.com/paper/2405.19024/) (2024)

## Abstract (arXiv)

Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-being, making these systems highly vulnerable to collapse under disruptions. In this context, this work studies cooperative resilience, understood as the system-level ability to maintain collective well-being under perturbations through adaptive agent behavior. We propose a framework for learning incentive structures aligned with collective well-being in multi-agent reinforcement learning systems, where reward functions shape individual decision-making and collective behavior. A resilience metric is used to score and rank agent trajectories, allowing the inference of reward functions that promote resilient collective behavior. These inferred reward functions are integrated into the multi-agent reinforcement learning process to shape agent interactions in social dilemma settings. The approach is evaluated in resource-sharing environments subject to disruptions, using three incentive structures: individual incentives, resilience-aligned incentives, and a hybrid incentive structure that combines both individual and collective components. The results show that the hybrid incentive structure promotes sustained collective behavior, reduces collapse events associated with resource depletion, and preserves system performance under disruption. These findings highlight the role of incentive design as a mechanism for promoting resilient collective behavior and provide a computational framework for multi-agent social dilemmas under disruptions.