Corpus ID: 221749529

Generalizing Emergent Communication.

@article{Unger2020GeneralizingEC,
  title={Generalizing Emergent Communication.},
  author={Thomas A. Unger and Elia Bruni},
  journal={arXiv: Artificial Intelligence},
  year={2020}
}
We converted the recently developed BabyAI grid world platform to a sender/receiver setup in order to test the hypothesis that established deep reinforcement learning techniques are sufficient to incentivize the emergence of a grounded discrete communication protocol between generalized agents. This is in contrast to previous experiments that employed straight-through estimation or specialized inductive biases. Our results show that these can indeed be avoided, by instead providing proper… Expand

References

SHOWING 1-10 OF 20 REFERENCES
Learning to Communicate with Deep Multi-Agent Reinforcement Learning
  • 630
  • PDF
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
  • 40
  • PDF
Evolving Culture vs Local Minima
  • 24
  • PDF
...
1
2
...