Hacker News
- OA: "How to Train Your OpenAI Five" ["800 petaflop/s-days and experienced about 45,000 years of Dota self-play over 10 realtime months"] https://openai.com/blog/how-to-train-your-openai-five/ 8 comments reinforcementlearning
Linking pages
- Solving Rubik’s Cube with a Robot Hand https://openai.com/blog/solving-rubiks-cube/ 53 comments
- Curiosity Killed the Mario http://www.michaelburge.us/2019/05/21/marai-agent.html 29 comments
- 10 Machine Learning Methods that Every Data Scientist Should Know | by Jorge Castañón | Towards Data Science https://medium.com/p/10-machine-learning-methods-that-every-data-scientist-should-know-3cc96e0eeee9 14 comments
- 10 Machine Learning Methods that Every Data Scientist Should Know | by Jorge Castañón | Towards Data Science https://towardsdatascience.com/10-machine-learning-methods-that-every-data-scientist-should-know-3cc96e0eeee9 9 comments
- How the “bigger is better” mentality damages AI research – TechTalks https://bdtechtalks.com/2019/11/25/ai-research-neural-networks-compute-costs/ 3 comments
- Collaborating with Humans Requires Understanding Them – The Berkeley Artificial Intelligence Research Blog https://bair.berkeley.edu/blog/2019/10/21/coordination/ 3 comments
Linked pages
- OpenAI Status https://status.openai.com 195 comments
- Learning Dexterity https://blog.openai.com/learning-dexterity/ 160 comments
- https://arena.openai.com/#/results 14 comments
- OpenAI Five Finals https://openai.com/blog/openai-five-finals/ 7 comments
- TrueSkill - Wikipedia https://en.wikipedia.org/wiki/TrueSkill 5 comments
Related searches:
Search whole site: site:openai.com
Search title: OpenAI Five Defeats Dota 2 World Champions
See how to search.