Using relative novelty to identify useful temporal abstractions in reinforcement learning

@inproceedings{Simsek2004UsingRN,
  title={Using relative novelty to identify useful temporal abstractions in reinforcement learning},
  author={{\"O}zg{\"u}r Simsek and Andrew G. Barto},
  booktitle={ICML},
  year={2004}
}
We present a new method for automatically creating useful temporal abstractions in reinforcement learning. We argue that states that allow the agent to transition to a different region of the state space are useful subgoals, and propose a method for identifying them using the concept of relative novelty. When such a state is identified, a temporally-extended activity (e.g., an option) is generated that takes the agent efficiently to this state. We illustrate the utility of the method in a… CONTINUE READING
Highly Cited
This paper has 191 citations. REVIEW CITATIONS

4 Figures & Tables

Topics

Statistics

01020'05'07'09'11'13'15'17
Citations per Year

192 Citations

Semantic Scholar estimates that this publication has 192 citations based on the available data.

See our FAQ for additional information.