# Learning Collective Action under Risk Diversity

arXiv: https://arxiv.org/abs/2201.12891 · HTML: https://mlsanity.com/paper/2201.12891/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 54 references that are in the map.
- First posted on arXiv 30 Jan 2022.

## Builds on (most cited first, 14 of 14)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/1709.04326/) (2017)
- [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)
- [The Mechanics of n-Player Differentiable Games](https://mlsanity.com/paper/1802.05642/) (2018)
- [Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.07169/) (2020)
- [Emergent Coordination Through Competition](https://mlsanity.com/paper/1902.07151/) (2019)
- [Stable Opponent Shaping in Differentiable Games](https://mlsanity.com/paper/1811.08469/) (2018)
- [Learning to Teach in Cooperative Multiagent Reinforcement Learning](https://mlsanity.com/paper/1805.07830/) (2018)
- [Timing uncertainty in collective risk dilemmas encourages group reciprocation and polarization](https://mlsanity.com/paper/2003.07317/) (2020)
- [Foolproof Cooperative Learning](https://mlsanity.com/paper/1906.09831/) (2019)

## Abstract (arXiv)

Collective risk dilemmas (CRDs) are a class of n-player games that represent societal challenges where groups need to coordinate to avoid the risk of a disastrous outcome. Multi-agent systems incurring such dilemmas face difficulties achieving cooperation and often converge to sub-optimal, risk-dominant solutions where everyone defects. In this paper we investigate the consequences of risk diversity in groups of agents learning to play CRDs. We find that risk diversity places new challenges to cooperation that are not observed in homogeneous groups. We show that increasing risk diversity significantly reduces overall cooperation and hinders collective target achievement. It leads to asymmetrical changes in agents' policies -- i.e. the increase in contributions from individuals at high risk is unable to compensate for the decrease in contributions from individuals at low risk -- which overall reduces the total contributions in a population. When comparing RL behaviors to rational individualistic and social behaviors, we find that RL populations converge to fairer contributions among agents. Our results highlight the need for aligning risk perceptions among agents or develop new learning techniques that explicitly account for risk diversity.