1
$\begingroup$

When describing the model architecture for a deep recurrent q network, the authors of the paper Learning to Communicate with Deep Multi-Agent Reinforcement Learning

each agent consists of a recurrent neural network (RNN), unrolled for $T$ time-steps, that maintains an internal state $h$, an input network for producing a task embedding $z$, and an output network for the Q-values and the messages $m$. The input for agent $a$ is defined as a tuple of $\left(o_{t}^{a}, m_{t-1}^{a^{\prime}}, u_{t-1}^{a}, a\right)$.

Can someone explain, in the context of RNNs, what the purpose of the embedding layer is here?

Implementation can be found here.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.