Incentivising cooperation by rewarding the weakest member
Autonomous agents that act with each other on behalf of humans are becoming more common in many social domains, such as customer service, transportation, and health care. In such social situations greedy strategies can reduce the positive outcome for all agents, such as leading to stop-and-go traffic on highways, or causing a denial of service on a communications channel. Instead, we desire autonomous decision-making for efficient performance while also considering equitability of the group to avoid these pitfalls. Unfortunately, in complex situations it is far easier to design machine learning objectives for selfish strategies than for equitable behaviors. Here we present a simple way to reward groups of agents in both evolution and reinforcement learning domains by the performance of their weakest member. We show how this yields ``fairer'' more equitable behavior, while also maximizing individual outcomes, and we show the relationship to biological selection mechanisms of group-level selection and inclusive fitness theory.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Antisocial pool rewarding does not deter public cooperation
Rewarding cooperation is in many ways expected behaviour from social players. However, strategies that promote antisocial behaviour are also surprisingly common, not just in human societies, but also among eusocial insec…
Weakest-link control of invasive species: Impacts of memory, bounded rationality and network structure in repeated cooperative games
The nature of dispersal of many invasive pests and pathogens in agricultural and forestry makes it necessary to consider how the actions of one manager affect neighbouring properties. In addition to the direct effects of…
Decision MakingManagementEmergent Cooperation in Quantum Multi-Agent Reinforcement Learning Using Communication
Emergent cooperation in classical Multi-Agent Reinforcement Learning has gained significant attention, particularly in the context of Sequential Social Dilemmas (SSDs). While classical reinforcement learning approaches h…
Multi-agent Reinforcement LearningIncentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training
Obtaining high-quality data for collaborative training of machine learning models can be a challenging task due to A) regulatory concerns and B) a lack of data owner incentives to participate. The first issue can be addr…
Federated LearningMultiagent Cooperation and Competition with Deep Reinforcement Learning
Multiagent systems appear in most social, economical, and political situations. In the present work we extend the Deep Q-Learning Network architecture proposed by Google DeepMind to multiagent environments and investigat…
Deep Reinforcement LearningQ-Learningreinforcement-learningReinforcement Learning+1