Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization

  title={Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization},
  author={Bram Bakker and J{\"u}rgen Schmidhuber},
We introduce a new method for hierarchical reinforcement learning. Highlevel policies automatically discover subgoals; low-level policies learn to specialize on different subgoals. Subgoals are represented as desired abstract observations which cluster raw input data. High-level value functions cover the state space at a coarse level; low-level value functions cover only parts of the state space at a fine-grained level. Experiments show that this method outperforms several flat reinforcement… CONTINUE READING
Highly Influential
This paper has highly influenced 13 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 125 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
79 Citations
12 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 79 extracted citations

126 Citations

Citations per Year
Semantic Scholar estimates that this publication has 126 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 12 references

Hierarchical reinforcement learning based on subgoal discovery and subpolicy specialization: First experiments with the HASSLE algorithm

  • B. Bakker, J. Schmidhuber
  • Technical report, IDSIA
  • 2003
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…