Skip to content

A
AAAI21_Emergent_language
Commit 153da1e2 by Xing
Options

Update theory.tex

parent 56daeae5
Showing with 1 additions and 1 deletions
AAAI2021/tex/theory.tex
...@@ -83,7 +83,7 @@ Algorithm~\ref{al:learning}, we train the separate Speaker $S$ and Listener $L$ ...@@ -83,7 +83,7 @@ Algorithm~\ref{al:learning}, we train the separate Speaker $S$ and Listener $L$
Stochastic Policy Gradient methodology in a tick-tock manner, i.e, training one Stochastic Policy Gradient methodology in a tick-tock manner, i.e, training one
agent while keeping the other one. Roughly, when training the Speaker, the agent while keeping the other one. Roughly, when training the Speaker, the
target is set to maximize the expected reward target is set to maximize the expected reward
$J(\theta_S, \theta_L)=E_{\pi_S,\pi_L}[R(t, t^)]$ by adjusting the parameter $J(\theta_S, \theta_L)=E_{\pi_S,\pi_L}[R(t, \hat{t})]$ by adjusting the parameter
$\theta_S$, where $\theta_S$ is the neural network parameters of Speaker $S$ $\theta_S$, where $\theta_S$ is the neural network parameters of Speaker $S$
with learned output probability distribution $\pi_S$, and $\theta_L$ is the with learned output probability distribution $\pi_S$, and $\theta_L$ is the
neural network parameters of Listener with learned probability distribution $\pi_L$. neural network parameters of Listener with learned probability distribution $\pi_L$.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment