Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Online Reinforcement Learning on CLEVR-Robot
Loading...
19.4
Reward
LaGO
2.344
6.772
11.2
15.628
Jun 23, 2026
Reward
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reward
Success Rate
LaGO
Task=Hard
2026.06
19.4
14
LaGO
Task=Easy
2026.06
14.8
14.8
Vanilla PPO
Task=Easy
2026.06
13.8
13.8
LaGO
Task=Overall Average
2026.06
12.2
27.2
Vanilla PPO
Task=Hard
2026.06
10.6
0.7
LaGO
Task=Real
2026.06
7.8
41.3
Vanilla PPO
Task=Overall Average
2026.06
7.6
15.1
LaGO
Task=Rephrase
2026.06
6.9
38.8
Vanilla PPO
Task=Real
2026.06
3
23
Vanilla PPO
Task=Rephrase
2026.06
3
23
Feedback
Search any
task
Search any
task