Open in app

Sign In

Write

Sign In

Dong Won (Don) Lee
Dong Won (Don) Lee

14 Followers

Home

About

Jul 7, 2021

C-Learning: No reward function needed for Goal-Conditioned RL

I was fortunate to come across a fascinating paper on C-Learning: Learning to Achieve Goals via Recursive Classification (Eysenbach, et. al) from ICLR 2021. I truly believe that the ideas presented in the paper are unique and valuable for many researchers in reinforcement learning. …

Machine Learning

10 min read

C-Learning: No reward function needed for Goal-Conditioned RL
C-Learning: No reward function needed for Goal-Conditioned RL
Machine Learning

10 min read


Published in The Startup

·Jun 3, 2020

Elegant Intuitions Behind Positional Encodings

How do we capture position and order of data? Key Intuition Behind Positional Encodings Introduction: Understanding the position and order is crucial in many tasks that involve sequences. Positional encoding play a crucial role in the widely known Transformer model (Vaswani, et al. 2019) because the architecture doesn’t naturally include the information about order of the…

Artificial Intelligence

6 min read

Elegant Intuitions Behind Positional Encodings
Elegant Intuitions Behind Positional Encodings
Artificial Intelligence

6 min read

Dong Won (Don) Lee

Dong Won (Don) Lee

14 Followers

thankful to be able to study what I love :)

Following
  • Synced

    Synced

  • Towards AI Editorial Team

    Towards AI Editorial Team

  • Walid Saba, PhD

    Walid Saba, PhD

  • Richard Kang

    Richard Kang

  • Robert Lange

    Robert Lange

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech