- Joined
- May 18, 1997
- Messages
- 55,601
We talked about OpenAI Five about a month ago and how five neural networks were being used to train its AI systems to play Dota 2. That same code base is being used to train robots. We are fairly sure that Finger Pivoting, Sliding, and Finger Gaiting will help train these robots to better latch onto your trachea for sure.
Check out the video.
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity. Our system, called Dactyl, is trained entirely in simulation and transfers its knowledge to reality, adapting to real-world physics using techniques we’ve been working on for the past year. Dactyl learns from scratch using the same general-purpose reinforcement learning algorithm and code as OpenAI Five. Our results show that it’s possible to train agents in simulation and have them solve real-world tasks, without physically-accurate modeling of the world.
Check out the video.
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity. Our system, called Dactyl, is trained entirely in simulation and transfers its knowledge to reality, adapting to real-world physics using techniques we’ve been working on for the past year. Dactyl learns from scratch using the same general-purpose reinforcement learning algorithm and code as OpenAI Five. Our results show that it’s possible to train agents in simulation and have them solve real-world tasks, without physically-accurate modeling of the world.