Incentivizing the Emergence of Grounded Discrete Communication Between General Agents. (arXiv:2001.01772v1 [cs.AI])

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 general agents. This is
in contrast to previous experiments that employed straight-through estimation
or tailored inductive biases. Our results show that these can indeed be
avoided, by instead providing proper environmental incentives. Moreover, they
show that a longer interval between communications incentivized more abstract
semantics. In some cases, the communicating agents adapted to new environments
more quickly than monolithic agents, showcasing the potential of emergent
discrete communication for transfer learning.

Source link

Related posts

Robotic mitral valve repair: 7-year surgical experience and mid-term follow-up results.


AI services startup Hypergiant brings on Bill Nye as an advisor


Artificial intelligence for cancer-associated thrombosis risk assessment – Author's reply.


This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More

Privacy & Cookies Policy