Jump to content

Skill chaining

From Wikipedia, the free encyclopedia
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Skill chaining is a skill discovery method in continuous reinforcement learning. It has been extended to high-dimensional continuous domains by the related Deep skill chaining algorithm.

References

  • Konidaris, George; Andrew Barto (2009). "Skill discovery in continuous reinforcement learning domains using skill chaining". Advances in Neural Information Processing Systems 22.
  • Bagaria, Akhil; George Konidaris (2020). "Option discovery using deep skill chaining". International Conference on Learning Representations.