Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density

@inproceedings{McGovern2001AutomaticDO,
  title={Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density},
  author={Amy McGovern and Andrew G. Barto},
  booktitle={ICML},
  year={2001}
}
This paper presents a method by which a reinforcement learning agent can automatically discover certain types of subgoals online. By creating useful new subgoals while learning, the agent is able to accelerate learning on the current task and to transfer its expertise to other, related tasks through the reuse of its ability to attain subgoals. The agent discovers subgoals based on commonalities across multiple paths to a solution. We cast the task of finding these commonalities as a multiple… CONTINUE READING
Highly Influential
This paper has highly influenced 26 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 416 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 269 extracted citations

417 Citations

0102030'99'03'08'13'18
Citations per Year
Semantic Scholar estimates that this publication has 417 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 16 references

acQuire-macros: An algorithm for automatically learning macro-actions

  • A. McGovern
  • NIPS 98 workshop on Abstraction and Hierarchy in…
  • 1998
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…