Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913369141805056 |
|---|---|
| author | Sarkar, Atrisha Muresanu, Andrei Ioan Blair, Carter Sharma, Aaryam Trivedi, Rakshit S Hadfield, Gillian K |
| author_facet | Sarkar, Atrisha Muresanu, Andrei Ioan Blair, Carter Sharma, Aaryam Trivedi, Rakshit S Hadfield, Gillian K |
| contents | Generative agents, which implement behaviors using a large language model (LLM) to interpret and evaluate an environment, has demonstrated the capacity to solve complex tasks across many social and technological domains. However, when these agents interact with other agents and humans in presence of social structures such as existing norms, fostering cooperation between them is a fundamental challenge. In this paper, we develop the framework of a 'Normative Module': an architecture designed to enhance cooperation by enabling agents to recognize and adapt to the normative infrastructure of a given environment. We focus on the equilibrium selection aspect of the cooperation problem and inform our agent design based on the existence of classification institutions that implement correlated equilibrium to provide effective resolution of the equilibrium selection problem. Specifically, the normative module enables agents to learn through peer interactions which of multiple candidate institutions in the environment, does a group treat as authoritative. By enabling normative competence in this sense, agents gain ability to coordinate their sanctioning behaviour; coordinated sanctioning behaviour in turn shapes primary behaviour within a social environment, leading to higher average welfare. We design a new environment that supports institutions and evaluate the proposed framework based on two key criteria derived from agent interactions with peers and institutions: (i) the agent's ability to disregard non-authoritative institutions and (ii) the agent's ability to identify authoritative institutions among several options. We show that these capabilities allow the agent to achieve more stable cooperative outcomes compared to baseline agents without the normative module, paving the way for research in a new avenue of designing environments and agents that account for normative infrastructure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19328 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation Sarkar, Atrisha Muresanu, Andrei Ioan Blair, Carter Sharma, Aaryam Trivedi, Rakshit S Hadfield, Gillian K Multiagent Systems Generative agents, which implement behaviors using a large language model (LLM) to interpret and evaluate an environment, has demonstrated the capacity to solve complex tasks across many social and technological domains. However, when these agents interact with other agents and humans in presence of social structures such as existing norms, fostering cooperation between them is a fundamental challenge. In this paper, we develop the framework of a 'Normative Module': an architecture designed to enhance cooperation by enabling agents to recognize and adapt to the normative infrastructure of a given environment. We focus on the equilibrium selection aspect of the cooperation problem and inform our agent design based on the existence of classification institutions that implement correlated equilibrium to provide effective resolution of the equilibrium selection problem. Specifically, the normative module enables agents to learn through peer interactions which of multiple candidate institutions in the environment, does a group treat as authoritative. By enabling normative competence in this sense, agents gain ability to coordinate their sanctioning behaviour; coordinated sanctioning behaviour in turn shapes primary behaviour within a social environment, leading to higher average welfare. We design a new environment that supports institutions and evaluate the proposed framework based on two key criteria derived from agent interactions with peers and institutions: (i) the agent's ability to disregard non-authoritative institutions and (ii) the agent's ability to identify authoritative institutions among several options. We show that these capabilities allow the agent to achieve more stable cooperative outcomes compared to baseline agents without the normative module, paving the way for research in a new avenue of designing environments and agents that account for normative infrastructure. |
| title | Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2405.19328 |