Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Real world #1

Open
stulp opened this issue May 21, 2021 · 0 comments
Open

Real world #1

stulp opened this issue May 21, 2021 · 0 comments

Comments

@stulp
Copy link

stulp commented May 21, 2021

As a roboticist, I am very interested in real-world reinforcement learning, and highly encourage all research directed at making RL work robustly and efficiently on physical robot systems. Your work certainly raises awareness for the issues that arise in doing so, and I think that's great.

With this background, I was also a bit surprised to find out that the real world you consider is a simulator. To me, the real world is the physical world that humans and robots physically occupy, rather than our simulations of this world, such as MuJoCo, Bullet, etc. (we cannot exclude that what we consider to be the real world is in fact a Matrix-like simulation, but let that philosophical byway not distract us here).

The issue to me is that if simulated worlds are now considered to be the "real world", I'm no longer sure how to call the world in which we roboticists conduct our experiments. What would you call this world?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant