DeepMind Blog company blog
Preserving Outputs Precisely while Adaptively Rescaling Targets
Multi-task learning - allowing a single agent to learn how to solve many different tasks - is a longstanding objective for artificial intelligence research. Recently, there has been a lot of excellent progress, with agents like DQN able to use the same algorithm to learn to play multiple games including Breakout and…
- Points
- 126
- HN comments
- 15
- Submissions
- 1
- Cited by
- 0 commenters
AI & Machine LearningSoftware Engineering2018
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Sep 13, 2018 | Preserving Outputs Precisely while Adaptively Rescaling Targets by DanielleMolloy | 126 | 15 |
