Hacker News new | past | comments | ask | show | jobs | submit login
Evolving Curricula with Regret-Based Environment Design (accelagent.github.io)
14 points by minch on March 4, 2022 | hide | past | favorite | 2 comments



Very interesting work and an amazing demo!! Btw, a very basic question: in the demo is there any curricula/training process being shown, or is it basically the final policies learned by each of the four competing approaches?

(ps: I co-wrote a short elementary paper on auto curricula design for RL in 2017 [0])

[0]: https://arxiv.org/abs/1703.07853


Thanks! The demo just shows the final agents after training (30K gradient updates). Interesting work re the reward maximizing curricula. I have not seen this before, so thanks for the pointer.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: