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

LunarLanderContinuous

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reinforcement LearningLunarLanderContinuous v2
Mean Reward533.6
65
Continuous ControlLunarLanderContinuous offline trajectories v2
Episodic Cumulative Reward254.55
35
Continuous ControlLunarLanderContinuous v3
Number of Active Parameters11.6
16
Reinforcement LearningLunarLanderContinuous v3
Mean Score308.03
4
Surrogate ModelingLunarLanderContinuous v3 (val)
Fidelity (%)96.84
4
Showing 5 of 5 rows