Commit 5401c11a by Zidong Du

~

parent 04e22e66
...@@ -24,35 +24,22 @@ In this paper, the task is xxxx. ...@@ -24,35 +24,22 @@ In this paper, the task is xxxx.
\textbf{Game rules} In our referential game, agents follow the following rules \textbf{Game rules} In our referential game, agents follow the following rules
to finish the game in a cooperatively manner. In each round,once received an to finish the game in a cooperatively manner. In each round,once received an
input object $t$, Speaker $S$ speaks a symbol sequence $s$ to Listener $L$ ; input object $t$, Speaker $S$ speaks a symbol sequence $s$ to Listener $L$ ;
Listener $L$ reconstruct the predict result $\hat{t}$ based on the listened Listener $L$ reconstruct the predicted result $\hat{t}$ based on the listened
sequence $s$; if $t=\hat{t}$, agents win this game and receive positive rewards sequence $s$; if $t=\hat{t}$, agents win this game and receive positive rewards
($R(t,\hat{t})=1$); otherwise agents fail this game and receive negative rewards ($R(t,\hat{t})=1$); otherwise agents fail this game and receive negative rewards
($R(t,\hat{t})=-1$). ($R(t,\hat{t})=-1$).
Precisely, Precisely, during the game, Speaker $S$ receives an input object $t$, which is
an expression with two words from the vocabulary set $V$, i.e., two
one-hot vector representing shape and color, respectively. Based on the $t$,
An input object t is a concept sequence with fixed length, denoted Speaker $S$ speaks a symbol sequence $s$, which similarly contains two words
$t=(c_0,c_1)$. from $V$. The Listener $L$ receives $s$ and output predicted result $\hat{t}$,
a single word (one-hot vector) selected from the Cartesian product of set two $V$s
The concept $c_0(shape)$ and $c_1(color)$ are indicated as a ($V\times V$), which representing all the meanings of two combined words from $V$.
one-hot vector respectively. Please note that since $t$ and $\hat{t}$ have different length, we say
The length of each one-hot vector ranges from 3 to 6. $t=\hat{t}$ if $t$ expresses the same meaning as $\hat{t}$, e.g.,
These two vectors are concatenated to denote the input object t. $t={[0,0,1],[0,1,0]}$ would be equal to $\hat{t}=[0,0,0,0,0,1]$ if they both mean ``red
Each symbol sequence s contains two words, denoted $(s_0,s_1)$. Each word $s_i$ circle''.
is chosen in the vocabulary set $V$. In this game, let the card $|V|$ range from
4 to 10, and the inequation $|V|^2\geq|M_1||M_1|$ is satisfied to ensure the
symbol sequence $(s_0,s_1)$ can be used to denote all the input object t. The
one-hot vector with the length $|V|$ is used to indicate the word $s_0$ and
$s_1$ respectively. Then, the two one-hot vectors are concatenated to denote the
symbol sequence s.
The predict result $\hat{t}$ is denoted as a one-hot vector with the length
$|M_0||M_1|$. Each bit of the one-hot vector denotes one input object. If the
predict result $\hat{t}[i*|M_1|+j]=1$, the one-hot vector of each predict
concept $\hat{c}_0$ and $\hat{c}_1$ respectively satisfied $\hat{c}_0[i]=1$ and
$\hat{c}_1[j]=1$.
If $(c_0,c_1)$ is equal to $(\hat{c}_0,\hat{c}_1)$, the input object and the
predict result indicate the same object.
......
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