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

Offline Reinforcement Learning on Antmaze

87.5Success Rate (umaze)

OPRIDE

75.85278.87681.984.924Feb 19, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.02
87.573.162.269.427.521.556.8
2026.02
85.569.163.865.718.714.352.8
2026.02
84.57872.55898.551.7
2026.02
77.56863.563.56.523.550.4
2026.02
76.372.5007.36.927.1