Human-Level Performance in 3D Multiplayer Games with Population-Based Reinforcement Learning. 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. 364(6443):859-865.
Human-Level Performance in 3D Multiplayer Games with Population-Based Reinforcement Learning [link]Paper  doi  abstract   bibtex   
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 Reinforcement learning (RL) has shown great success in increasingly complex single-agent environments and two-player turn-based games. However, the real world contains multiple agents, each learning and acting independently to cooperate and compete with other agents. We used a tournament-style evaluation to demonstrate that an agent can achieve human-level performance in a three-dimensional multiplayer first-person video game, Quake III Arena in Capture the Flag mode, using only pixels and game points scored as input. We used a two-tier optimization process in which a population of independent RL agents are trained concurrently from thousands of parallel matches on randomly generated environments. Each agent learns its own internal reward signal and rich representation of the world. These results indicate the great potential of multiagent reinforcement learning for artificial intelligence research. Teams of artificial agents compete successfully against humans in the video game Quake III Arena in Capture the Flag mode. Teams of artificial agents compete successfully against humans in the video game Quake III Arena in Capture the Flag mode.
@article{jaderbergHumanlevelPerformance3D2019,
  langid = {english},
  title = {Human-Level Performance in {{3D}} Multiplayer Games with Population-Based Reinforcement Learning},
  volume = {364},
  issn = {0036-8075, 1095-9203},
  url = {https://science.sciencemag.org/content/364/6443/859},
  doi = {10.1126/science.aau6249},
  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
Reinforcement learning (RL) has shown great success in increasingly complex single-agent environments and two-player turn-based games. However, the real world contains multiple agents, each learning and acting independently to cooperate and compete with other agents. We used a tournament-style evaluation to demonstrate that an agent can achieve human-level performance in a three-dimensional multiplayer first-person video game, Quake III Arena in Capture the Flag mode, using only pixels and game points scored as input. We used a two-tier optimization process in which a population of independent RL agents are trained concurrently from thousands of parallel matches on randomly generated environments. Each agent learns its own internal reward signal and rich representation of the world. These results indicate the great potential of multiagent reinforcement learning for artificial intelligence research.
Teams of artificial agents compete successfully against humans in the video game Quake III Arena in Capture the Flag mode.
Teams of artificial agents compete successfully against humans in the video game Quake III Arena in Capture the Flag mode.},
  number = {6443},
  journaltitle = {Science},
  urldate = {2019-06-03},
  date = {2019-05-31},
  pages = {859-865},
  author = {Jaderberg, Max and Czarnecki, Wojciech M. and Dunning, Iain and Marris, Luke and Lever, Guy and Castañeda, Antonio Garcia and Beattie, Charles and Rabinowitz, Neil C. and Morcos, Ari S. and Ruderman, Avraham and Sonnerat, Nicolas and Green, Tim and Deason, Louise and Leibo, Joel Z. and Silver, David and Hassabis, Demis and Kavukcuoglu, Koray and Graepel, Thore},
  file = {/home/dimitri/Nextcloud/Zotero/storage/BKW8SC9N/Jaderberg et al. - 2019 - Human-level performance in 3D multiplayer games wi.pdf;/home/dimitri/Nextcloud/Zotero/storage/PHLALIVP/859.html},
  eprinttype = {pmid},
  eprint = {31147514}
}
Downloads: 0