AI Weekly Malaysia

Back to items Summaries

Reinforcement learning with prediction-based rewards

ID
910
Status
new
Published
31 Oct 2018, 3:00 PM
Fetched
27 Jun 2026, 7:47 PM
Provider
OpenAI News
Category
ai-labs
Original URL
https://openai.com/index/reinforcement-learning-with-prediction-based-rewards
Source URL
https://openai.com/news/rss.xml

Excerpt

We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.

Summary

No summary yet. It will appear after the daemon summarizes this item.

Top