AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning
DeepMind's new agent to tackle yet another Esport: Starcraft II. This agent uses deep reinforcement learning with a new technique, called League Training, to catapult itself to Grandmaster-level skill at playing this game.
Abstract:
Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an important challenge for artificial intelligence research, owing to its iconic and enduring status among the most difficult professional esports and its relevance to the real world in terms of its raw complexity and multi-agent challenges. Over the course of a decade and numerous competitions, the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems. Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks. We evaluated our agent, AlphaStar, in the full game of StarCraft II, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8% of officially ranked human players.
Authors: Oriol Vinyals, Igor Babuschkin, Wojciech M. Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H. Choi, Richard Powell, Timo Ewalds, Petko Georgiev, Junhyuk Oh, Dan Horgan, Manuel Kroiss, Ivo Danihelka, Aja Huang, Laurent Sifre, Trevor Cai, John P. Agapiou, Max Jaderberg, Alexander S. Vezhnevets, Rémi Leblond, Tobias Pohlen, Valentin Dalibard, David Budden, Yury Sulsky, James Molloy, Tom L. Paine, Caglar Gulcehre, Ziyu Wang, Tobias Pfaff, Yuhuai Wu, Roman Ring, Dani Yogatama, Dario Wünsch, Katrina McKinney, Oliver Smith, Tom Schaul, Timothy Lillicrap, Koray Kavukcuoglu, Demis Hassabis, Chris Apps, David Silver
https://www.deepmind.com/blog/article/AlphaStar-Grandmaster-level-in-StarCraft-II-using-multi-agent-reinforcement-learning
Links:
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
BitChute: https://www.bitchute.com/channel/yannic-kilcher
Minds: https://www.minds.com/ykilcher
Видео AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning канала Yannic Kilcher
Abstract:
Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an important challenge for artificial intelligence research, owing to its iconic and enduring status among the most difficult professional esports and its relevance to the real world in terms of its raw complexity and multi-agent challenges. Over the course of a decade and numerous competitions, the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems. Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks. We evaluated our agent, AlphaStar, in the full game of StarCraft II, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8% of officially ranked human players.
Authors: Oriol Vinyals, Igor Babuschkin, Wojciech M. Czarnecki, Michaël Mathieu, Andrew Dudzik, Junyoung Chung, David H. Choi, Richard Powell, Timo Ewalds, Petko Georgiev, Junhyuk Oh, Dan Horgan, Manuel Kroiss, Ivo Danihelka, Aja Huang, Laurent Sifre, Trevor Cai, John P. Agapiou, Max Jaderberg, Alexander S. Vezhnevets, Rémi Leblond, Tobias Pohlen, Valentin Dalibard, David Budden, Yury Sulsky, James Molloy, Tom L. Paine, Caglar Gulcehre, Ziyu Wang, Tobias Pfaff, Yuhuai Wu, Roman Ring, Dani Yogatama, Dario Wünsch, Katrina McKinney, Oliver Smith, Tom Schaul, Timothy Lillicrap, Koray Kavukcuoglu, Demis Hassabis, Chris Apps, David Silver
https://www.deepmind.com/blog/article/AlphaStar-Grandmaster-level-in-StarCraft-II-using-multi-agent-reinforcement-learning
Links:
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
BitChute: https://www.bitchute.com/channel/yannic-kilcher
Minds: https://www.minds.com/ykilcher
Видео AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning канала Yannic Kilcher
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
ReBeL - Combining Deep Reinforcement Learning and Search for Imperfect-Information Games (Explained)How AlphaStar Became a StarCraft Grandmaster | AI and GamesAlphaStar explained: Grandmaster level in StarCraft II with multi-agent RL[ML News] DeepMind does Nowcasting | The Guardian's shady reporting | AI finishes Beethoven's 10thSinGAN: Learning a Generative Model from a Single Natural ImageDoes GPT-3 lie? - Misinformation and fear-mongering around the TruthfulQA datasetAlphaStar: The inside storyAlphaZero, chess and AI learning[ML News] Stanford HAI coins Foundation Models & High-profile case of plagiarism uncoveredDeepMind StarCraft II Demonstration∞-former: Infinite Memory Transformer (aka Infty-Former / Infinity-Former, Research Paper Explained)AlphaStar VS GRANDMASTER MECH!МИРОВОЙ РЕКОРД: 78 ядерных ударов на Чемпионате мира по StarCraft II[Classic] Generative Adversarial Networks (Paper Explained)ALiBi - Train Short, Test Long: Attention with linear biases enables input length extrapolationBig Transfer (BiT): General Visual Representation Learning (Paper Explained)DeepMind’s AlphaStar Beats Humans 10-0 (or 1)Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess (Paper Explained)Discovering Symbolic Models from Deep Learning with Inductive Biases (Paper Explained)