Human-level performance in 3D multiplayer games with population-based reinforcement learning
Open accessAbstract
Artificial teamwork: Artificially intelligent agents are getting better and better at two-player games, but most real-world endeavors require teamwork. Jaderberg et al. designed a computer program that excels at playing the video game Quake III Arena in Capture the Flag mode, where two multiplayer teams compete in capturing the flags of the opposing team. The agents were trained by playing thousands of games, gradually learning successful strategies not unlike those favored by their human counterparts. Computer agents competed successfully against humans even when their reaction times were slowed to match those of humans. Science , this issue p. 859
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · see citing works
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · see citing works
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · see citing works
Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
Sutton, R. S., Precup, D., & Singh, S. (1999) · Artificial Intelligence · doi:10.1016/s0004-3702(99)00052-1 · Cited by 3,119 · see citing works
Temporal difference learning and TD-Gammon
Tesauro, G. (1995) · Communications of the ACM · doi:10.1145/203330.203343 · Cited by 1,618 · cited 1× · see citing works
“Recent progress in artificial intelligence through reinforcement learning (RL) has shown great success on increasingly complex single-agent environments ( 30, 40, 45, 46, 56 ) and two-player turn-based games ( 47, 58, 66 ).”
BackgroundIncreasing Speed of Processing With Action Video Games
Dye, M. W. G., Green, C. S., & Bavelier, D. (2009) · Current Directions in Psychological Science · doi:10.1111/j.1467-8721.2009.01660.x · Cited by 521 · see citing works
Concept cells: the building blocks of declarative memory functions
Quiroga, R. Q. (2012) · Nature reviews. Neuroscience · doi:10.1038/nrn3251 · Cited by 472 · cited 1× · see citing works
“We also found individual neurons whose activations coded directly for some of these features, e.g. a neuron that was active if and only if the agent’s teammate was holding the flag, reminiscent of concept cells ( 51 ).”
BackgroundEmergence of grounded compositional language in multi-agent populations
Mordatch, I., & Abbeel, P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11492 · Cited by 440 · see citing works
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
Lanctot, M., Zambaldi, V., Gruslys, A., Lazaridou, A., Tuyls, K., Perolat, J., Silver, D., & Graepel, T. (2017) · arXiv · doi:10.48550/arxiv.1711.00832 · Cited by 295 · see citing works
Self-citationLearning with Opponent-Learning Awareness
Foerster, J., Chen, R. Y., Al-Shedivat, M., Whiteson, S., Abbeel, P., & Mordatch, I. (2018) · International Joint Conference on Autonomous Agents and Multiagent Systems · doi:10.65109/hgwa8807 · Cited by 215 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Grandmaster level in StarCraft II using multi-agent reinforcement learning
Vinyals, O., Babuschkin, I., Czarnecki, W. M., Mathieu, M., Dudzik, A., Chung, J., Choi, D. H., Powell, R., Ewalds, T., Georgiev, P., et al. (2019) · Nature · doi:10.1038/s41586-019-1724-z · Cited by 3,455 · see citing works
Self-citationDota 2 with Large Scale Deep Reinforcement Learning
OpenAI, :, Berner, C., Brockman, G., Chan, B., Cheung, V., Dębiak, P., Dennison, C., Farhi, D., Fischer, Q., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.06680 · Cited by 1,065 · see citing works
Reinforcement learning, fast and slow
Botvinick, M., Ritter, S., Wang, J. X., Kurth-Nelson, Z., Blundell, C., & Hassabis, D. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2019.02.006 · Cited by 667 · see citing works
Self-citationBeyond Accuracy: The Role of Mental Models in Human-AI Team Performance
Bansal, G., Nushi, B., Kamar, E., Lasecki, W. S., Weld, D. S., & Horvitz, E. (2019) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v7i1.5285 · Cited by 466 · see citing works
Reinforcement Learning and Its Applications in Modern Power and Energy Systems: A Review
Cao, D., Hu, W., Zhao, J., Zhang, G., Zhang, B., Liu, Z., Chen, Z., & Blaabjerg, F. (2020) · Journal of Modern Power Systems and Clean Energy · doi:10.35833/mpce.2020.000552 · Cited by 460 · see citing works
Emergent Tool Use From Multi-Agent Autocurricula
Baker, B., Kanitscheider, I., Markov, T., Wu, Y., Powell, G., McGrew, B., & Mordatch, I. (2019) · arXiv · doi:10.48550/arxiv.1909.07528 · Cited by 424 · see citing works
“Our work sees itself in the tradition of previous studies that showcase emergent complexity in simple physically grounded environments [11, 12, 13, 14]; the success in these settings inspires confidence that inducing autocurricula in physically grounded and open-ended environments could eventually enable agents to acq…”
BackgroundMethodDirect Fit to Nature: An Evolutionary Perspective on Biological and Artificial Neural Networks
Hasson, U., Nastase, S. A., & Goldstein, A. (2020) · Neuron · doi:10.1016/j.neuron.2019.12.002 · Cited by 387 · see citing works
Compute Trends Across Three Eras of Machine Learning
Sevilla, J., Heim, L., Ho, A., Besiroglu, T., Hobbhahn, M., & Villalobos, P. (2022) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891914 · Cited by 363 · see citing works
Deep reinforcement learning and its neuroscientific implications
Botvinick, M., Wang, J. X., Dabney, W., Miller, K. J., & Kurth-Nelson, Z. (2020) · Neuron · doi:10.1016/j.neuron.2020.06.014 · Cited by 269 · see citing works
From attribution maps to human-understandable explanations through Concept Relevance Propagation
Achtibat, R., Dreyer, M., Eisenbraun, I., Bosse, S., Wiegand, T., Samek, W., & Lapuschkin, S. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00711-8 · Cited by 181 · see citing works
Ethical considerations about artificial intelligence for prognostication in intensive care
Beil, M., Proft, I., van Heerden, D., Sviri, S., & van Heerden, P. V. (2019) · Intensive Care Medicine Experimental · doi:10.1186/s40635-019-0286-6 · Cited by 124 · see citing works
Hierarchical Reinforcement Learning: A Survey and Open Research Challenges
Hutsebaut-Buysse, M., Mets, K., & Latré, S. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4010009 · Cited by 129 · see citing works
Open Problems in Cooperative AI
Dafoe, A., Hughes, E., Bachrach, Y., Collins, T., McKee, K. R., Leibo, J. Z., Larson, K., & Graepel, T. (2020) · arXiv · doi:10.48550/arxiv.2012.08630 · Cited by 93 · see citing works
Self-citationClune, J. (2019) · arXiv · doi:10.48550/arxiv.1905.10985 · Cited by 82 · see citing works
Verkhivker, G. M., Agajanian, S., Hu, G., & Tao, P. (2020) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2020.00136 · Cited by 76 · see citing works
Collective intelligence for deep learning: A survey of recent developments
Ha, D., & Tang, Y. (2022) · Collective Intelligence · doi:10.1177/26339137221114874 · Cited by 71 · see citing works
Macrae, C. (2022) · Risk Analysis · doi:10.1111/risa.13850 · Cited by 76 · see citing works
Leibo, J. Z., Hughes, E., Lanctot, M., & Graepel, T. (2019) · arXiv · doi:10.48550/arxiv.1903.00742 · Cited by 60 · see citing works
Self-citationSocial Diversity and Social Preferences in Mixed-Motive Reinforcement Learning
McKee, K. R., Gemp, I., McWilliams, B., Duèñez-Guzmán, E. A., Hughes, E., & Leibo, J. Z. (2020) · International Joint Conference on Autonomous Agents and Multiagent Systems · doi:10.65109/dnuf7773 · Cited by 33 · see citing works
Self-citationHuman-Timescale Adaptation in an Open-Ended Task Space
Adaptive Agent Team, Bauer, J., Baumli, K., Baveja, S., Behbahani, F., Bhoopchand, A., Bradley-Schmieg, N., Chang, M., Clay, N., Collister, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.07608 · Cited by 19 · see citing works
“…also been works that use auto-curricula over co-players, although these typically focus on singleton environments (Vinyals et al., 2019; Berner et al., 2019) or uniformly sampled tasks (Baker et al., 2020; Jaderberg et al., 2019; Liu et al., 2019; Cultural General Intelligence Team et al., 2022).”
BackgroundHabitat 3.0: A Co-Habitat for Humans, Avatars, and Robots
Puig, X., Undersander, E., Szot, A., Cote, M. D., Yang, T.-Y., Partsey, R., Desai, R., Clegg, A. W., Hlavac, M., Min, S. Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.13724 · Cited by 15 · see citing works
“…multi-agent reinforcement learning (MARL) works operate in a low-dimensional state space (e.g., grid-like mazes, tabular tasks, or Markov games) (Jaderberg et al., 2019; Samvelyan et al., 2019; oai; Resnick et al., 2018; Suarez et al., 2019; Baker et al., 2020; Giles & Jim, 2002; Lazaridou et…”
BackgroundInfluentialMulti-Agent Risks from Advanced AI
Hammond, L., Chan, A., Clifton, J., Hoelscher-Obermaier, J., Khan, A., McLean, E., Smith, C., Barfuss, W., Foerster, J., Gavenčiak, T., et al. (2025) · arXiv · doi:10.48550/arxiv.2502.14143 · Cited by 10 · see citing works
Self-citationEmergence of Collaborative Hunting via Multi-Agent Deep Reinforcement Learning
Tsutsui, K., Takeda, K., & Fujii, K. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-37660-3_15 · Cited by 5 · see citing works
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Samvelyan, M., Khan, A., Dennis, M., Jiang, M., Parker-Holder, J., Foerster, J., Raileanu, R., & Rocktäschel, T. (2023) · arXiv · doi:10.48550/arxiv.2303.03376 · Cited by 8 · see citing works
“Randomly modifying the environment has proven critical for the emergence of complex behaviours in Hide-and-Seek (Baker et al., 2019), Capture the Flag (Jaderberg et al., 2019), and StarCraft II Unit Micromanagement (Ellis et al., 2022).”
BackgroundEnvironment Complexity and Nash Equilibria in a Sequential Social Dilemma
Yasir, M., Howes, A., Mavroudis, V., & Hicks, C. (2024) · arXiv · doi:10.48550/arxiv.2408.02148 · Cited by 1 · see citing works
“MARL methods have shown considerable success both in competitive environments [9, 32] and in purely cooperative environments [27, 4].”
Background
- Authors
- Jaderberg, M., Czarnecki, W. M., Dunning, I., Marris, L., Lever, G., Castañeda, A. G., Beattie, C., Rabinowitz, N. C., Morcos, A. S., Ruderman, A., Sonnerat, N., Green, T., Deason, L., Leibo, J. Z., Silver, D., Hassabis, D., Kavukcuoglu, K., & Graepel, T.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- DeepMind, London, UK.
- Corresponding author
- Jaderberg, Max
- Czarnecki, Wojciech M.
- Dunning, Iain
- ORCID
- Venue
- Science
- Published
- 2019-05-31
- Volume
- 364
- Issue
- 6443
- Pages
- 859-865
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W2810602713
- Cited by
- 662
- References
- 10
- Citations by year
- 2026: 37 · 2025: 58 · 2024: 86 · 2023: 72 · 2022: 86 · 2021: 128 · 2020: 118 · 2019: 69 · 2018: 8
- FWCI
- 45.73
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- multiplayer games, Capture the Flag, human-level performance, video game agents
- MeSH terms
- Machine Learning, Reinforcement, Psychology, Reward, Video Games
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
