Learning Dexterous Manipulation with a Robotic Hand with Alex Paino скачать в хорошем качестве

Learning Dexterous Manipulation with a Robotic Hand with Alex Paino

Teaching complex robots, such as a humanoid robotic hand to solve dexterous manipulation tasks is a very difficult and long-standing problem in robotics. At the same time, solving this problem would unlock a huge new set of applications for robotics. In this talk we will highlight the progress the Robotics team at OpenAI has made towards solving this problem over the past few years. We will begin by describing our first release in this research program, "Learning Dexterity", and then we will cover our latest release, "Solving Rubik's cube with a robotic hand". Finally, we will conclude with a smaller result in which we learn control policies aimed at solving the task in "Learning Dexterity" but in an end-to-end fashion (i.e. directly from images). Alex has been a member of the Robotics team at OpenAI since early 2019, where he has worked on a variety of problems in computer vision and RL. Prior to joining OpenAI, he was a machine learning engineer at Sift Science, a startup that provides fraud and abuse prevention products. Read the blog post on this project: https://openai.com/blog/solving-rubik... Follow Alex on Twitter:   / atpaino   This presentation was a part of our Virtual Deep Learning Salon, to sign up for updates on these join our meetup and slack community! http://wandb.me/meetups http://wandb.me/fs 👩🏼‍🚀Weights and Biases: Record and visualize every detail of your research, collaborate easily, advance the state of the art - we’re always free for academics and open source projects. Email carey@wandb.com with any questions or feature suggestions. Blog: https://www.wandb.com/articles Gallery: See what you can create with W&B -https://app.wandb.ai/gallery Continue the conversation on our slack community - http://wandb.me/fs