Machine Learning Pwns Old-School Atari Games
Science Talk
Scientific American
4.2 • 644 Ratings
🗓️ 25 February 2021
⏱️ 8 minutes
🧾️ Download transcript
Summary
Transcript
Click on a timestamp to play from that location
| 0:00.0 | Understanding the human body is a team effort. That's where the Yachtel group comes in. |
| 0:05.8 | Researchers at Yachtolt have been delving into the secrets of probiotics for 90 years. |
| 0:11.0 | Yacold also partners with nature portfolio to advance gut microbiome science through the global grants for gut health, an investigator-led research program. |
| 0:19.6 | To learn more about Yachtolt, visit yawcult.co.j.p. |
| 0:23.9 | That's y-A-K-U-L-T.C-O.J-P. |
| 0:28.4 | When it comes to a guide for your gut, count on Yacolt. |
| 0:35.0 | This is Scientific American's 60-second science. I'm Pachina Maimer. |
| 0:39.3 | Whether you're a pro-gamer or you dip your toes into that world every once in a while, Chances are you got stuck while playing a video game |
| 0:55.9 | once or was even gloriously defeated by one. I know I have. Maybe in your frustration you kicked |
| 1:03.5 | the console a little. Maybe you took it out on the controllers or if you're an 80s kid like me |
| 1:09.4 | made the joystick pay. |
| 1:12.9 | Now a group of computer scientists from Uber AI are taking revenge for all of us who've been |
| 1:18.6 | in this situation before. Using a family of simple algorithms stacked Go-Explorer, they went |
| 1:25.1 | back and beat some of the most notoriously difficult Atari games |
| 1:29.0 | whose chunky blocks of pixels and 8-bit tunes had once challenged, taunted, and even enraged |
| 1:35.9 | us. But what does revisiting those games from the 80s and 90s accomplish besides fulfilling a childhood fantasy? |
| 1:47.3 | According to the scientists who publish their work in nature, |
| 1:50.9 | experimenting with solving video games that require a complex, hard exploration gives way to better learning algorithms. |
| 1:58.7 | They become more intelligent and perform better under real-world scenarios. |
| 2:03.6 | One of the nice things of Go-Explorer is that it's not just limited to video games, |
| 2:10.3 | but that you can also apply it to practical applications like robotics. |
| 2:15.3 | That was Joost Hazenka, one of the principal researchers at Uber AI. |
... |
Please login to see the full transcript.
Disclaimer: The podcast and artwork embedded on this page are from Scientific American, and are the property of its owner and not affiliated with or endorsed by Tapesearch.
Generated transcripts are the property of Scientific American and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.
Copyright © Tapesearch 2026.

