List your company

ResearchFormerly WizWand

Worst-case time-constrained reinforcement learning

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

Agg. Average across environments (test)

Oracle-TC-M2TD3

3.07Worst-case Reward

12

Feb 26, 2026

Walker MuJoCo (test)

Stacked-TC-M2TD3

1.69Normalized Worst-Case Reward

12

Feb 26, 2026

Humanoid MuJoCo (test)

4.02Normalized Worst-Case Reward

12

Feb 26, 2026

Hopper MuJoCo (test)

Oracle-TC-M2TD3

7.79Normalized Worst-Case Reward

12

Feb 26, 2026

HalfCheetah MuJoCo (test)

Oracle-TC-M2TD3

2.76Normalized Worst-Case Reward

12

Feb 26, 2026

Ant MuJoCo (test)

1.66Normalized Worst-Case Reward

12

Feb 26, 2026