EasyDeepLearn

OpenAI's Rubik's Cube robot — key techniques.

hard

Answer

  • OpenAI 2019.
  • (1) PPO in simulation with Automatic Domain Randomization (ADR): progressively harder randomization of physics parameters.
  • (2) LSTM policy inferring physical parameters online.
  • (3) Kociemba's algorithm for cube solution planning; RL for physical manipulation.
  • (4) Sim-to-real via ADR made a single-hand manipulation robust to real-world variation.
  • Demonstrated sim2real at scale for high-dimensional dexterous manipulation.
Check yourself — multiple choice
  • Random
  • PPO in sim + Automatic Domain Randomization (progressively harder physics rand) + LSTM inferring physics online; sim2real for dexterous manipulation of Rubik's cube by one hand
  • Same as PPO
  • Not real

OpenAI Rubik: PPO + ADR + LSTM sim2real for dexterous manipulation.

#applications

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions