In looking at an algorithm in the paper Learning to Communicate with Deep Multi-Agent Reinforcement Learning.

Here is the full algorithm:

enter image description here

What does the notation for t=T to 1,−1 do: refer to in terms of time steps?

The network structure is a deep recurrent q network.

Secondly, why do the gradients need to be reset to zero?

  • 2
    $\begingroup$ That notation should mean to go from time step $T$ to time step $1$ by a negative step $-1$, i.e. backward, so $T$, then $T-1$, then $T-2$, and so on until $1$. If you know Python, this should be familiar. However, note that this is just a guess because I am not familiar with this algorithm. $\endgroup$ – nbro Jul 3 at 13:23
  • $\begingroup$ Yes, this makes sense, and fits the problem. Thank you! $\endgroup$ – kikram Jul 3 at 17:41

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.