Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Embodied Task Completion on ALFWorld out-of-distribution (test)
Loading...
0.81
Task Success Score (Cool)
Meta-RL
0.41272
0.51586
0.619
0.72214
Dec 18, 2025
Task Success Score (Cool)
Task Success Rate (Pick2)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Task Success Score (Cool)
Task Success Rate (Pick2)
Meta-RL
Framework=LAMER, Train...
2025.12
0.81
0.502
RL
Framework=LAMER, Train...
2025.12
0.581
0.36
Prompting
Type=Prompting-based
2025.12
0.428
0.212
Feedback
Search any
task
Search any
task
