Corpus ID: 218763395

Novel Policy Seeking with Constrained Optimization

@article{Sun2020NovelPS,
  title={Novel Policy Seeking with Constrained Optimization},
  author={Hao Sun and Zhenghao Peng and Bo Dai and Jian Guo and Dahua Lin and Bolei Zhou},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10696}
}
  • Hao Sun, Zhenghao Peng, +3 authors Bolei Zhou
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • In this work, we address the problem of learning to seek novel policies in reinforcement learning tasks. Instead of following the multi-objective framework used in previous methods, we propose to rethink the problem under a novel perspective of constrained optimization. We first introduce a new metric to evaluate the difference between policies, and then design two practical novel policy seeking methods following the new perspective, namely the Constrained Task Novel Bisector (CTNB), and the… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 57 REFERENCES

    Constrained Policy Optimization

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    VIME: Variational Information Maximizing Exploration

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL