Multi-agent Reinforcement Learning in Sequential Social Dilemmas
Open accessThe DOI matches its OpenAlex record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. Cooperativeness is a property that applies to policies, not elementary actions. We introduce sequential social dilemmas that share the mixed incentive structure of matrix game social dilemmas but also require agents to learn policies that implement their strategic intentions. We analyze the dynamics of policies learned by multiple self-interested independent learning agents, each using its own deep Q-network, on two Markov games we introduce here: 1. a fruit Gathering game and 2. a Wolfpack hunting game. We characterize how learned behavior in each domain changes as a function of environmental factors including resource abundance. Our experiments show how conflict can emerge from competition over shared resources and shed light on how the sequential nature of real world social dilemmas affects cooperation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Evolution of Reciprocal Altruism
Trivers, R. L. (1971) · The Quarterly Review of Biology · doi:10.1086/406755 · Cited by 11,010
Evolution of indirect reciprocity by image scoring
Nowak, M. A., & Sigmund, K. (1998) · Nature · doi:10.1038/31225 · Cited by 2,700
Daw, N. D., Niv, Y., & Dayan, P. (2005) · Nature Neuroscience · doi:10.1038/nn1560 · Cited by 2,533
A simple rule for the evolution of cooperation on graphs and social networks
Ohtsuki, H., Hauert, C., Lieberman, E., & Nowak, M. A. (2006) · Nature · doi:10.1038/nature04605 · Cited by 2,208
A strategy of win-stay, lose-shift that outperforms tit-for-tat in the Prisoner's Dilemma game
Nowak, M., & Sigmund, K. (1993) · Nature · doi:10.1038/364056a0 · Cited by 1,797
Tit for tat in heterogeneous populations
Nowak, M. A., & Sigmund, K. (1992) · Nature · doi:10.1038/355250a0 · Cited by 1,029
Cited by
Nguyen, T. T., Nguyen, N. D., & Nahavandi, S. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2977374 · Cited by 1,306
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
Zhang, K., Yang, Z., & Başar, T. (2021) · Studies in Systems, Decision and Control · doi:10.1007/978-3-030-60990-0_12 · Cited by 1,264
Multi-agent deep reinforcement learning: a survey
Gronauer, S., & Diepold, K. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-09996-w · Cited by 957
A survey and critique of multiagent deep reinforcement learning
Hernandez-Leal, P., Kartal, B., & Taylor, M. E. (2019) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-019-09421-1 · Cited by 671
Q-Learning Algorithms: A Comprehensive Classification and Applications
Jang, B., Kim, M., Harerimana, G., & Kim, J. W. (2019) · IEEE Access · doi:10.1109/access.2019.2941229 · Cited by 635
Metadata
- Authors
- Leibo, J. Z., Zambaldi, V., Lanctot, M., Marecki, J., & Graepel, T.
- Venue
- arXiv (Cornell University)
- Publisher
- Cornell University
- Published
- 2017-05-08
- Pages
- 464-473
- ISSN
- 2331-8422 (ISSN-L)
- DOI
- 10.5555/3091125.3091194
- OpenAlex
- W2964345382
- Cited by
- 150
- References
- 6
- Type
- posted content
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Multi-agent Reinforcement Learning in Sequential Social Dilemmas. https://app.cochat.ai/papers/10.5555/3091125.3091194
- The paper
- Leibo, J. Z., Zambaldi, V., Lanctot, M., Marecki, J., & Graepel, T. (2017). Multi-agent Reinforcement Learning in Sequential Social Dilemmas. arXiv (Cornell University). https://doi.org/10.5555/3091125.3091194
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.