Corpus ID: 219721507

Opponent Modelling with Local Information Variational Autoencoders

@article{Papoudakis2020OpponentMW,
  title={Opponent Modelling with Local Information Variational Autoencoders},
  author={Georgios Papoudakis and Filippos Christianos and Stefano V. Albrecht},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.09447}
}
  • Georgios Papoudakis, Filippos Christianos, Stefano V. Albrecht
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Modelling the behaviours of other agents (opponents) is essential for understanding how agents interact and making effective decisions. Existing methods for opponent modelling commonly assume knowledge of the local observations and chosen actions of the modelled opponents, which can significantly limit their applicability. We propose a new modelling technique based on variational autoencoders which uses only the local observations of the agent under control: its observed world state, chosen… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    Asynchronous Methods for Deep Reinforcement Learning

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Auto-Encoding Variational Bayes

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Auto-encoding variational bayes. International Conference on Learning Representations

    • P Diederik, Max Kingma, Welling
    • 2014