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
Chcete-li přidat komentář, přihlaste se
Ostatní příspěvky v této skupině
Article URL: https://openai.com/index/introducing-o3-and-o4-mini/
Article URL: https://microsoft.design/articles/introducing-kermit-a-typeface-for-kids/
Comments URL:
Hi HN — we’re Nathalie, Dalton, Vince, and Matt, and we’re launching Jasmine Energy (https://www.jasmine.energy), a tool that helps residential and commerc
