홈 › Papers

Dota 2 with Large Scale Deep Reinforcement Learning

2019-12-13 · Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemysław Dębiak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Chris Hesse, Rafal Józefowicz, Scott Gray, Catherine Olsson, Jakub Pachocki, Michael Petrov, Henrique Pondé de Oliveira Pinto, Jonathan Raiman, Tim Salimans, Jeremy Schlatter, Jonas Schneider, Szymon Sidor, Ilya Sutskever, Jie Tang, Filip Wolski, Susan Zhang

On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game. The game of Dota 2 presents novel challenges for AI systems such as long time horizons, imperfect information, and complex, continuous state-action spaces, all challenges which will become increasingly central to more capable AI systems. OpenAI Five leveraged existing reinforcement learning techniques, scaled to learn from batches of approximately 2 million frames every 2 seconds. We developed a distributed training system and tools for continual training which allowed us to train OpenAI Five for 10 months. By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task.

📄 PDF Abstract BibTeX arXiv:1912.06680

Code (1)

bilibili/LastOrder-Dota2

Tasks

Deep Reinforcement LearningDota 2reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

DOTA: A Large-scale Dataset for Object Detection in Aerial Images

2017-11-28 · CVPR 2018 6 · Gui-Song Xia, Xiang Bai, Jian Ding, Zhen Zhu 외

Object detection is an important and challenging problem in computer vision. Although the past decade has witnessed major advances in object detection in natural scenes, such successes have been slow to aerial imagery, n…

Earth Observation Object object-detection Object Detection+1

Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges

2021-02-24 · Jian Ding, Nan Xue, Gui-Song Xia, Xiang Bai 외

In the past decade, object detection has achieved significant progress in natural images but not in aerial images, due to the massive variations in the scale and orientation of objects caused by the bird's-eye view of ae…

Object object-detection Object Detection Object Detection In Aerial Images

An Empirical Model of Large-Batch Training

2018-12-14 · Sam McCandlish, Jared Kaplan, Dario Amodei, OpenAI Dota Team

In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data paralle…

Dota 2 model Reinforcement Learning

Towards Playing Full MOBA Games with Deep Reinforcement Learning

2020-11-25 · NeurIPS 2020 12 · Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen 외

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has…

AI Agent Deep Reinforcement Learning Dota 2 reinforcement-learning+2

Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II

2021-09-26 · Michał Opanowicz

Recently, multiple approaches for creating agents for playing various complex real-time computer games such as StarCraft II or Dota 2 were proposed, however, they either embed a significant amount of expert knowledge int…

GPU Starcraft Starcraft II