Random MDP
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
400-State Random MDP on-policy
24.74Sum of sqrt MSE
7
400-State Random MDP (off-policy)
0.11MSE
7
400-State Random MDP on-policy
0.07MSE
7
400-State Random MDP off-policy
29.65Sum of sqrt MSE
6