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

TextFrozenLake

Benchmarks

Task NameDataset NameSOTA ResultTrend
Embodied Task CompletionTextFrozenLake 4×4; h=0.9
Cumulative Return265.2
7
Sequential Decision MakingTextFrozenLake 4x4; h=0.9
Cumulative Return31.8
5
Text-based Reinforcement Learning NavigationTextFrozenLake 4x4
Normalized Success Rate100
5
Showing 3 of 3 rows