Hi everyone!
After spending hundreds of hours, we're excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfully completes the game using a policy under 10M parameters, PPO, and a few novel techniques. With the release of Claude Plays Pokémon, now feels like the perfect time to showcase our work.
We'd love to get feedback!
Comments URL: https://news.ycombinator.com/item?id=43269330
Points: 41
# Comments: 26
Login to add comment
Other posts in this group
Article URL: https://docs.evidence.dev/components/all-components/
Article URL: https://v4.zod.dev/v4
Comments URL: https://news.ycombinator.com/item?id=43667925
Article URL: https://protesilaos.com/emacs/emacs-lisp-elements
Article URL: https://arktype.io/
Comments URL: https://news.ycombinator.com/item?id=43665540
Article URL: https://github.com/cdhooper/kicksmash32
Comments URL: https://news
