Hierarchical Reinforcement Learning System

A Hierarchical Reinforcement Learning System is a Reinforcement Learning System that is based on a hierarchical structure.

• Context:
  • It can be used to train modular neural networks by attributing different levels in the hierarchy to each module.
• Example(s):
  • Feudal Reinforcement Learning (FRL) System.
  • …
• Counter-Example(s):
  • Adversarial Learning System.
• See: FeUdal Network, LeakGAN, Maze Task, Worker Neural Network, Manager Neural Network.

---

---

References

2017

• (Vezhnevets et al., 2017) ⇒ Alexander Sasha Vezhnevets, Simon Osindero, Tom Schaul, Nicolas Heess, Max Jaderberg, David Silver, and Koray Kavukcuoglu. (2017). “FeUdal Networks for Hierarchical Reinforcement Learning.” In: Proceedings of the 34th International Conference on Machine Learning (ICML2017).

1992

• (Dayan & Hinton, 1992) ⇒ Peter Dayan, and Geoffrey E. Hinton. (1992). “Feudal Reinforcement Learning.” In: Proceedings of Advances in Neural Information Processing Systems 5 (NIPS 1992).

---