A review of cooperation in multi-agent learning

Y Du, JZ Leibo, U Islam, R Willis, P Sunehag - arXiv preprint arXiv …, 2023 - arxiv.org
Cooperation in multi-agent learning (MAL) is a topic at the intersection of numerous
disciplines, including game theory, economics, social sciences, and evolutionary biology …

Robustness and adaptability of reinforcement learning-based cooperative autonomous driving in mixed-autonomy traffic

R Valiente, B Toghi, R Pedarsani… - IEEE Open Journal of …, 2022 - ieeexplore.ieee.org
Building autonomous vehicles (AVs) is a complex problem, but enabling them to operate in
the real world where they will be surrounded by human-driven vehicles (HVs) is extremely …

[HTML][HTML] Mathematical frameworks for the analysis of norms

A Sontuoso - Current Opinion in Psychology, 2024 - Elsevier
Research into society's informal rules of conduct, or norms, has recently experienced a
surge, extending across multiple academic disciplines. Despite this growth, the theoretical …

Get it in writing: Formal contracts mitigate social dilemmas in multi-agent rl

PJK Christoffersen, AA Haupt… - arXiv preprint arXiv …, 2022 - arxiv.org
Multi-agent reinforcement learning (MARL) is a powerful tool for training automated systems
acting independently in a common environment. However, it can lead to sub-optimal …

Formal contracts mitigate social dilemmas in multi-agent reinforcement learning

A Haupt, P Christoffersen, M Damani… - Autonomous Agents and …, 2024 - Springer
Abstract Multi-agent Reinforcement Learning (MARL) is a powerful tool for training
autonomous agents acting independently in a common environment. However, it can lead to …

The emergence of division of labour through decentralized social sanctioning

A Yaman, JZ Leibo, G Iacca… - Proceedings of the …, 2023 - royalsocietypublishing.org
Human ecological success relies on our characteristic ability to flexibly self-organize into
cooperative social groups, the most successful of which employ substantial specialization …

Investigating the impact of direct punishment on the emergence of cooperation in multi-agent reinforcement learning systems

N Dasgupta, M Musolesi - arXiv preprint arXiv:2301.08278, 2023 - arxiv.org
Solving the problem of cooperation is of fundamental importance to the creation and
maintenance of functional societies, with examples of cooperative dilemmas ranging from …

Learning Optimal" Pigovian Tax" in Sequential Social Dilemmas

Y Hua, S Gao, W Li, B Jin, X Wang, H Zha - arXiv preprint arXiv …, 2023 - arxiv.org
In multi-agent reinforcement learning, each agent acts to maximize its individual
accumulated rewards. Nevertheless, individual accumulated rewards could not fully reflect …

Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity

M Smit, FP Santos - arXiv preprint arXiv:2408.04549, 2024 - arxiv.org
Altruistic cooperation is costly yet socially desirable. As a result, agents struggle to learn
cooperative policies through independent reinforcement learning (RL). Indirect reciprocity …

Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning

S Ha, H Jeong - International Conference on Machine …, 2023 - proceedings.mlr.press
How have individuals of social animals in nature evolved to learn from each other, and what
would be the optimal strategy for such learning in a specific environment? Here, we address …