From the Blog

Research notes, product updates and ideas from EXEPERT AI.

Tagged #reinforcement-learning

5 on this page

Jumper, the Jumping Crab Robot: What Is Open Source, What Isn't, and What You Can Do Without One

#robotics #crab-robot #open-source #open-hardware #reinforcement-learning #sim-to-real #mujoco #robot-simulation #kingkong-robotics #fact-check

Akmal Alif

13 October 2026

Dwarkesh Patel Revisits Sutton: Imitation as a Prior, and the Gap Nobody Disputes

#exepert-updates #reinforcement-learning #richard-sutton #dwarkesh-patel #continual-learning #world-models #bitter-lesson

Akmal Alif

9 October 2026

Hide and Seek: How Simple Competition Taught AI Agents to Use Tools

#reinforcement-learning #multi-agent #self-play #autocurricula #emergent-behaviour #openai #tool-use

Akmal Alif

8 October 2026

Two Languages of Intelligence: Reading the Sutton–Dwarkesh Interview

#rich-sutton #dwarkesh-patel #reinforcement-learning #llms #world-models #the-bitter-lesson #ai-research

Akmal Alif

7 October 2026

The Bitter Lesson for Embodied AI

#rich-sutton #the-bitter-lesson #embodied-ai #reinforcement-learning #ai-research

Akmal Alif

Featured10 September 2026