List your company

Continuous Control on Humanoid 1M v5

793.1Average Episodic RewardPDA
666.22699.16732.1765.04Mar 10, 2026

Evaluation results

MethodLinks
PDAEnvironment steps=1M, Seeds=10, Tests per epoch=102026.03793.1
PPOEnvironment steps=1M, Seeds=10, Tests per epoch=102026.03671.1