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

Stochastic GridWorld

Benchmarks

Task NameDataset NameSOTA ResultTrend
Optimal policy selectionStochastic Gridworld (S=16, A=4)
PCS100
28
Reinforcement LearningStochastic GridWorld (20% slip probability) (test)
Success Rate85
5
Showing 2 of 2 rows