Hierarchical Reinforcement Learning

22 October 2017

Theory

• Sutton, Richard S., Doina Precup, and Satinder Singh. “Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning.” Artificial intelligence 112.1-2 (1999): 181-211.
• Parr, Ronald, and Stuart J. Russell. “Reinforcement learning with hierarchies of machines.” Advances in neural information processing systems. 1998.

Hierarchical Action Space

• Andre, David, and Stuart J. Russell. “State abstraction for programmable reinforcement learning agents.” AAAI/IAAI. 2002.
• Marthi, Bhaskara, et al. “Concurrent hierarchical reinforcement learning.” IJCAI. 2005.

Lookahead in the Hierarchical Action Space

• Marthi, Bhaskara, Stuart J. Russell, and Jason Andrew Wolfe. “Angelic Hierarchical Planning: Optimal and Online Algorithms.” ICAPS. 2008.

[back]