List your company

ResearchFormerly WizWand

Reinforcement Learning Surrogate Modeling

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Pendulum (P) (test)

95Reward Ratio

8

Jul 9, 2026

HalfCheetah (HC) (test)

85Reward Ratio

4

Jul 9, 2026

Hopper H (test)

89Reward Ratio

4

Jul 9, 2026

Swimmer (S) (test)

101Reward Ratio

4

Jul 9, 2026

Reacher (R) (test)

81Reward Ratio

4

Jul 9, 2026

InvertedDoublePendulum (IDP) (test)

103Reward Ratio (%)

4

Jul 9, 2026

LunarLander (LL) (test)

90Reward Ratio

4

Jul 9, 2026

MountainCar (MC) (test)

99Reward Ratio

4

Jul 9, 2026