Research &ag视讯厅开户网址

There is no development without research

Research work is an essential part of  and a key aspect of the company’s development. Our projects bring fresh ideas to AI research, an area of human thought and production we believe is worth contributing to. In collaboration with top universities, scientific institutions and global corporations, we have made crucial contributions to the field of Reinforcement Learning.

AG视讯国际厅发牌员

ag视讯国际厅
  • Trained a number of action-conditioned video models which are used as neural simulators of Atari environments
  • Trained Atari agents using learned neural simulators and tested the performance of the agents in original environments
  • Compared the performance of our agents to performance of agents trained using two model-free algorithms Rainbow and PPO and 100K and 500K interactions with the environment
  • Invited presentations at the University of Oxford, DeepMind and Google Brain Zurich

ag亚游视讯厅

ag真人视讯国际厅
  • Conducted parallel training of Atari games on one of the largest European supercomputers
  • Held the world record in parallel training of Atari games for two months in 2018 (beaten by DeepMind)
  • Presented work at the leading European HPC conference and were cited by DeepMind

ag视讯厅注册

ag视讯厅
  • Modeled a dozen real-life routes in Unreal Engine 4
  • Parallelized computations in order to generate hundreds of millions of frames using Unreal Engine 4 and one of the biggest European supercomputers
  • Models we trained were deployed on real autonomous vehicles multiple times in 2018 and 2019

ag视讯国际厅

ag视讯厅官网开户
  • The first time reinforcement learning has been convincingly applied to solving general mathematical problems on a large scale
  • Published a paper in collaboration with researchers from the Technical
  • University in Prague and the University of Innsbruck
  • Presented at the main track of NeurIPS 2018

AG视讯厅欢乐捕鱼

AG视讯国际厅发牌员
  • Achieved state-of-the-art results in environments known for challenging exploration
  • Presented at the  Deep RL and Imitation Learning Workshops at NeurIPS 2018

ag视讯直播厅

ag视讯厅娱乐
  • Trained walking gaits with reinforcement learning methods
  • Took 6th place out of 400+ teams in the Learning to Run challenge, NIPS, 2017

ag真人视讯厅一台

ag亚游厅跟ag视讯
  • Developed an original RL algorithm for hierarchical reinforcement learning; presented at Google Headquarters in Mountain View during the Robot Learning conference, 2017

ag视讯厅平台开户

澳门ag视讯厅开户
  • , Inc.
  • 2100 Geng Road, Suite 210
  • Palo Alto, CA 94303
  • United States of America
  • Sp. z o.o.
  • Al. Jerozolimskie 162A
  • 02-342 Warsaw
  • Poland
AG视讯贵宾厅
ag真人视讯国际厅




You can modify your privacy settings and unsubscribe from our lists at any time (see our privacy policy).

This site is protected by reCAPTCHA and the Google privacy policy and terms of service apply.