2000 character limit reached
Emergent Resource Exchange and Tolerated Theft Behavior using Multi-Agent Reinforcement Learning
Published 4 Jul 2023 in cs.MA and cs.NE | (2307.01862v1)
Abstract: For decades, the evolution of cooperation has piqued the interest of numerous academic disciplines such as game theory, economics, biology, and computer science. In this work, we demonstrate the emergence of a novel and effective resource exchange protocol formed by dropping and picking up resources in a foraging environment. This form of cooperation is made possible by the introduction of a campfire, which adds an extended period of congregation and downtime for agents to explore otherwise unlikely interactions. We find that the agents learn to avoid getting cheated by their exchange partners, but not always from a third party. We also observe the emergence of behavior analogous to tolerated theft, despite the lack of any punishment, combat, or larceny mechanism in the environment.
- Melting Pot 2.0. ArXiv:2211.13746 [cs].
- Robert M. Axelrod. 1984. The evolution of cooperation. Basic books, New York.
- Emergent Tool Use From Multi-Agent Autocurricula. ArXiv:1909.07528 [cs, stat].
- Learning Robust Real-Time Cultural Transmission without Human Data. ArXiv:2203.00715 [cs].
- Joshua M. Epstein and Robert Axtell. 1996. Growing Artificial Societies: Social Science from the Bottom Up. Brookings Institution Press. Google-Books-ID: xXvelSs2caQC.
- Sevan G Ficici and Jordan B Pollack. 1998. Challenges in Coevolutionary Learning: Arms-Race Dynamics, Open-Endedness, and Mediocre Stable States. Proceedings of the sixth international conference on Artificial life, page 10.
- Jon Gauthier and Igor Mordatch. 2016. A Paradigm for Situated and Goal-Driven Language Learning.
- Umberto Gostoli and Eric Silverman. 2023. Self-Isolation and Testing Behaviour During the COVID-19 Pandemic: An Agent-Based Model. Artificial Life, 29(1):94–117.
- Stephen Jay Gould and Niles Eldredge. 1977. Punctuated equilibria: the tempo and mode of evolution reconsidered. Paleobiology, 3(2):115–151. 2228 citations (Semantic Scholar/DOI) [2022-11-05].
- Dynamic population-based meta-learning for multi-agent communication with natural language. 35th Conference on Neural Information Processing Systems, page 14.
- Joseph Henrich. 2021. WEIRDest People in the World.
- Joseph Patrick Henrich. 2016. The secret of our success: how culture is driving human evolution, domesticating our species, and making us smarter. Princeton University Press, Princeton. OCLC: ocn908084074.
- Martin Hinsch and Jakub Bijak. 2023. The Effects of Information on the Formation of Migration Routes and the Dynamics of Migration. Artificial Life, 29(1):3–20.
- Inequity aversion improves cooperation in intertemporal social dilemmas. arXiv:1803.08884 [cs, q-bio]. ArXiv: 1803.08884.
- Glynn Isaac. 1978. The Food-sharing Behavior of Protohuman Hominids. Scientific American, 238(4):90–108.
- Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning. arXiv:1810.08647 [cs, stat]. ArXiv: 1810.08647.
- Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning. Number: arXiv:2205.06760 arXiv:2205.06760 [cs].
- Food Sharing Among Ache Foragers: Tests of Explanatory Hypotheses [and Comments and Reply]. Current Anthropology, 26(2):223–246.
- Daan Klijn and A. E. Eiben. 2021. A coevolutionary approach to deep multi-agent reinforcement learning. ArXiv:2104.05610 [cs].
- Angeliki Lazaridou and Marco Baroni. 2020. Emergent Multi-Agent Communication in the Deep Learning Era. arXiv:2006.02419 [cs]. ArXiv: 2006.02419.
- Multi-Agent Cooperation and the Emergence of (Natural) Language. arXiv:1612.07182 [cs]. ArXiv: 1612.07182.
- Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research. Number: arXiv:1903.00742 arXiv:1903.00742 [cs, q-bio].
- Malthusian Reinforcement Learning. ArXiv:1812.07019 [cs, q-bio].
- Kristian Lindren. 1992. Evolutionary phenomena in simple dynamics. pages 295–312. Artificial Life.
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. arXiv:1706.02275 [cs]. ArXiv: 1706.02275.
- Deep reinforcement learning models the emergent dynamics of human cooperation. arXiv:2103.04982 [cs]. ArXiv: 2103.04982.
- Generative Agents: Interactive Simulacra of Human Behavior. ArXiv:2304.03442 [cs].
- Social Simulacra: Creating Populated Prototypes for Social Computing Systems. ArXiv:2208.04024 [cs].
- Tidor-Vlad Pricope. 2021. Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review. ArXiv:2106.00123 [cs, q-fin].
- QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning.
- Ray. https://github.com/ray-project/ray.
- Proximal Policy Optimization Algorithms. ArXiv:1707.06347 [cs].
- Kenneth O. Stanley and Joel Lehman. 2015. Why Greatness Cannot Be Planned: The Myth of the Objective. Springer International Publishing, Cham.
- Joseph Suarez and Phillip Isola. 2022. SPECIALIZATION AND EXCHANGE IN NEURAL MMO.
- Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning. ArXiv:1712.06567 [cs].
- A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings. ArXiv:2106.09012 [cs].
- Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? Number: arXiv:2011.09533 arXiv:2011.09533 [cs].
- The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games. arXiv:2103.01955 [cs]. ArXiv: 2103.01955.
- The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies. ArXiv:2004.13332 [cs, econ, q-fin, stat].
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.