Corpus ID: 52156937

Emergence of Communication in an Interactive World with Consistent Speakers

@article{Bogin2018EmergenceOC,
  title={Emergence of Communication in an Interactive World with Consistent Speakers},
  author={Ben Bogin and Mor Geva and Jonathan Berant},
  journal={ArXiv},
  year={2018},
  volume={abs/1809.00549}
}
  • Ben Bogin, Mor Geva, Jonathan Berant
  • Published 2018
  • Computer Science
  • ArXiv
  • Training agents to communicate with one another given task-based supervision only has attracted considerable attention recently, due to the growing interest in developing models for human-agent interaction. Prior work on the topic focused on simple environments, where training using policy gradient was feasible despite the non-stationarity of the agents during training. In this paper, we present a more challenging environment for testing the emergence of communication from raw pixels, where… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
    • 51
    • Open Access
    On the Pitfalls of Measuring Emergent Communication
    • 40
    • Highly Influenced
    • Open Access
    Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
    • 38
    • Open Access
    Measuring Compositionality in Representation Learning
    • 33
    • Open Access
    Ease-of-Teaching and Language Structure from Emergent Communication
    • 17
    • Open Access
    Emergent Multi-Agent Communication in the Deep Learning Era
    • 1
    • Open Access
    Developmentally motivated emergence of compositional communication via template transfer
    • 1
    • Open Access
    On Voting Strategies and Emergent Communication
    • 1
    On Emergent Communication in Competitive Multi-Agent Teams
    • 1
    • Open Access
    Emergent Communication with World Models

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES
    Asynchronous Methods for Deep Reinforcement Learning
    • 3,275
    • Highly Influential
    • Open Access
    Simple statistical gradient-following algorithms for connectionist reinforcement learning
    • 2,884
    • Highly Influential
    • Open Access
    The Mathematics of Statistical Machine Translation: Parameter Estimation
    • 4,390
    • Highly Influential
    • Open Access
    On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
    • 2,738
    • Highly Influential
    • Open Access
    Child's Talk: Learning to Use Language
    • 1,890
    Understanding Natural Language
    • 2,247
    • Open Access
    Multi-Agent Cooperation and the Emergence of (Natural) Language
    • 192
    • Open Access
    Action-Conditional Video Prediction using Deep Networks in Atari Games
    • 542
    • Open Access
    Does the chimpanzee have a theory of mind? 30 years later
    • 3,061
    • Open Access
    Emergence of Grounded Compositional Language in Multi-Agent Populations
    • 263
    • Open Access