Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Interactive Task Learning on ALFWorld (val_seen)

97.7Pick Success Rate

GiGPOw/std

2.22827.01451.876.586Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
97.798.889.382.783.779.290.8
2026.06
96.795.78794.410081.792.7
2026.06
94.410079.782.291.293.391.9
2026.06
92.982.966.772.785.46577.3
2026.06
92.392.580.36489.568.880.4
2026.06
91.267.133.351.533.357.557.6
2026.06
90.889.372.566.174.764.777.6
2026.06
88.37166.452.862.856.969.7
2026.06
87.687.371.978.281.348.975.5
2026.06
85.384.559.753.778.253.572.8
2026.06
83.294.684.182.284.291.787.5
2026.06
64.857.146.440.560.647.454.4
2026.06
6244.936.341.630.923.842.7
2026.06
48.534.318.235.413.217.631.2
2026.06
35.321.719.422.213.63.721.8
2026.06
33.419.32.821.66.93.214.8
2026.06
17.415.77.720.56.2212.8
2026.06
5.93.34.25.59.704.1