How an unlikely corner of robotics research, locomotion, defined RL's new notion of success.
How close are we in the real world to robots that can begin to self-learn? Does the evolution of large language models ever overlap with robotics?
Errm, a bit too broad of a question. The broad answer is yes to both, but that's not particularly insightful.
Haha okay. I guess I'll keep bugging you with questions just the same.
I think it is in a good accordance to this article to post this youtube video here:
https://youtu.be/xAXvfVTgqr0
A robot that self-learnd real time (no simulation) using model-based Dreamer RL algorithm. It is not strictly an LLM, although it contains lots of transformers.
How close are we in the real world to robots that can begin to self-learn? Does the evolution of large language models ever overlap with robotics?
Errm, a bit too broad of a question. The broad answer is yes to both, but that's not particularly insightful.
Haha okay. I guess I'll keep bugging you with questions just the same.
I think it is in a good accordance to this article to post this youtube video here:
https://youtu.be/xAXvfVTgqr0
A robot that self-learnd real time (no simulation) using model-based Dreamer RL algorithm. It is not strictly an LLM, although it contains lots of transformers.