Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Random MDP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Policy Evaluation400-State Random MDP on-policy
Sum of sqrt MSE24.74
7
Policy Evaluation400-State Random MDP (off-policy)
MSE0.11
7
Policy Evaluation400-State Random MDP on-policy
MSE0.07
7
Policy Evaluation400-State Random MDP off-policy
Sum of sqrt MSE29.65
6
Showing 4 of 4 rows