Jack Monas
commited on
Commit
·
c2e844a
1
Parent(s):
29924b3
rules
Browse files
app.py
CHANGED
@@ -1,5 +1,58 @@
|
|
1 |
import streamlit as st
|
2 |
import pandas as pd
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
def main():
|
4 |
st.set_page_config(page_title="World Model Challenge")
|
5 |
|
@@ -34,27 +87,7 @@ def main():
|
|
34 |
st.write(
|
35 |
"The Evaluation Challenge tackles the ultimate question: Can you predict a robot's performance in the real world without physically deploying it? In this challenge, you will be provided with many different policies for a specific task. Your task is to rank these policies according to their expected real-world performance. This ranking will be compared with the actual ranking of the policies."
|
36 |
)
|
37 |
-
|
38 |
-
st.markdown("### Scoring")
|
39 |
-
st.write(
|
40 |
-
"Our scoring system rewards strong performance across all challenges, with extra weight given to the Evaluation Challenge. "
|
41 |
-
"The breakdown is as follows:\n\n"
|
42 |
-
"**Compression Challenge**\n"
|
43 |
-
"- 1st Place: 10 points\n"
|
44 |
-
"- 2nd Place: 7 points\n"
|
45 |
-
"- 3rd Place: 5 points\n\n"
|
46 |
-
"**Sampling Challenge**\n"
|
47 |
-
"- 1st Place: 10 points\n"
|
48 |
-
"- 2nd Place: 7 points\n"
|
49 |
-
"- 3rd Place: 5 points\n\n"
|
50 |
-
"**Evaluation Challenge**\n"
|
51 |
-
"- 1st Place: 20 points\n"
|
52 |
-
"- 2nd Place: 14 points\n"
|
53 |
-
"- 3rd Place: 10 points\n\n"
|
54 |
-
"The overall winner will be the team with the highest total points. In the event of a tie, the following tie-breakers will be applied in order:\n\n"
|
55 |
-
"1. Highest Evaluation Challenge score\n"
|
56 |
-
"2. Highest Sampling Challenge score\n\n"
|
57 |
-
)
|
58 |
st.write(
|
59 |
"The overall leaderboard, which displays the total points accumulated across all challenges, will be launched on March 10th. Below is a preview of the leaderboard format:"
|
60 |
)
|
|
|
1 |
import streamlit as st
|
2 |
import pandas as pd
|
3 |
+
|
4 |
+
|
5 |
+
|
6 |
+
def scoring_layout():
|
7 |
+
st.markdown("## Scoring")
|
8 |
+
st.write(
|
9 |
+
"Our scoring system rewards strong performance across all challenges, with extra weight "
|
10 |
+
"given to the Evaluation Challenge. The breakdown is as follows:"
|
11 |
+
)
|
12 |
+
|
13 |
+
# Create three columns for a more interesting layout
|
14 |
+
col1, col2, col3 = st.columns(3)
|
15 |
+
|
16 |
+
with col1:
|
17 |
+
st.markdown("### Compression Challenge")
|
18 |
+
st.markdown(
|
19 |
+
"""
|
20 |
+
- **1st Place**: 10 points
|
21 |
+
- **2nd Place**: 7 points
|
22 |
+
- **3rd Place**: 5 points
|
23 |
+
"""
|
24 |
+
)
|
25 |
+
|
26 |
+
with col2:
|
27 |
+
st.markdown("### Sampling Challenge")
|
28 |
+
st.markdown(
|
29 |
+
"""
|
30 |
+
- **1st Place**: 10 points
|
31 |
+
- **2nd Place**: 7 points
|
32 |
+
- **3rd Place**: 5 points
|
33 |
+
"""
|
34 |
+
)
|
35 |
+
|
36 |
+
with col3:
|
37 |
+
st.markdown("### Evaluation Challenge")
|
38 |
+
st.markdown(
|
39 |
+
"""
|
40 |
+
- **1st Place**: 20 points
|
41 |
+
- **2nd Place**: 14 points
|
42 |
+
- **3rd Place**: 10 points
|
43 |
+
"""
|
44 |
+
)
|
45 |
+
|
46 |
+
st.markdown("---")
|
47 |
+
st.markdown("### Tie-Breakers")
|
48 |
+
st.write(
|
49 |
+
"The overall winner will be the team with the highest total points. "
|
50 |
+
"In the event of a tie, the following tie-breakers will be applied in order:\n\n"
|
51 |
+
"1. Highest Evaluation Challenge score\n"
|
52 |
+
"2. Highest Sampling Challenge score\n\n"
|
53 |
+
"If teams remain tied after these two criteria, a panel review will determine the final ranking."
|
54 |
+
)
|
55 |
+
|
56 |
def main():
|
57 |
st.set_page_config(page_title="World Model Challenge")
|
58 |
|
|
|
87 |
st.write(
|
88 |
"The Evaluation Challenge tackles the ultimate question: Can you predict a robot's performance in the real world without physically deploying it? In this challenge, you will be provided with many different policies for a specific task. Your task is to rank these policies according to their expected real-world performance. This ranking will be compared with the actual ranking of the policies."
|
89 |
)
|
90 |
+
scoring_layout()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
st.write(
|
92 |
"The overall leaderboard, which displays the total points accumulated across all challenges, will be launched on March 10th. Below is a preview of the leaderboard format:"
|
93 |
)
|