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
Войдите, чтобы добавить комментарий
Другие сообщения в этой группе
Article URL: https://docs.z.ai/guides/llm/glm-4.5
Comments URL: https://news.ycomb
Article URL: https://www.bbc.com/news/articles/c4gzl41rpdqo
Article URL: https://www.twz.com/air/10-f-35s-deploying-to-puert
Article URL: https://community.hubitat.com/t/nest-1st-gen-and-2n
Article URL: http://www.atlasoftheuniverse.com/12lys.html
Comments URL: ht
