Human-level performance in 3D multiplayer games with population-based reinforcement learning-Reference-Cited by-同舟云学术

Human-level performance in 3D multiplayer games with population-based reinforcement learning

Published:2019-05-31 Issue:6443 Volume:364 Page:859-865
ISSN:0036-8075
Container-title:Science
language:en
Short-container-title:Science

Author:

Jaderberg Max¹^ORCID,Czarnecki Wojciech M.¹^ORCID,Dunning Iain¹^ORCID,Marris Luke¹,Lever Guy¹^ORCID,Castañeda Antonio Garcia¹^ORCID,Beattie Charles¹^ORCID,Rabinowitz Neil C.¹,Morcos Ari S.¹^ORCID,Ruderman Avraham¹^ORCID,Sonnerat Nicolas¹,Green Tim¹^ORCID,Deason Louise¹^ORCID,Leibo Joel Z.¹^ORCID,Silver David¹,Hassabis Demis¹,Kavukcuoglu Koray¹,Graepel Thore¹^ORCID

Affiliation:

1. DeepMind, London, UK.

Abstract

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

Publisher

American Association for the Advancement of Science (AAAS)

Subject

Multidisciplinary

Reference82 articles.

1. Human-level control through deep reinforcement learning

2. V. Mnih et al . Proc. Int. Conf. Mach. Learn. 48 pp. 1928–1937 (2016).

3. J. Schulman F. Wolski P. Dhariwal A. Radford O. Klimov Proximal policy optimization algorithms. arXiv:1707.06347 [cs.LG] (2017).

4. T. P. Lillicrap et al . Continuous control with deep reinforcement learning. Proc. Int. Conf. Learn. Rep . (2016).

5. M. Jaderberg et al . Reinforcement learning with unsupervised auxiliary tasks. Proc. Int. Conf. Learn. Rep . (2017).

Cited by 325 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Survey on Collaborative Task Assignment for Heterogeneous UAVs Based on Artificial Intelligence Methods;CAAI Artificial Intelligence Research;2024-12

2. Sequential action-induced invariant representation for reinforcement learning;Neural Networks;2024-11

3. Cooperative coevolution for non-separable large-scale black-box optimization: Convergence analyses and distributed accelerations;Applied Soft Computing;2024-11

4. Towards the development of believable agents: Adopting neural architectures and adaptive neuro-fuzzy inference system via playback of human traces;Journal of King Saud University - Computer and Information Sciences;2024-10

5. Learning and Fast Adaptation for Air Combat Decision with Improved Deep Meta-reinforcement Learning;International Journal of Aeronautical and Space Sciences;2024-09-09