List your company

Game Playing on Biased RPS Standard (test)

17.9ExploitabilityPPO-EMAg
16.61625.28333.9542.617Jun 22, 2026

Evaluation results

MethodLinks
PPO-EMAgPolicy selection strategy=Magnet2026.0617.9
PPO-EMAgPolicy selection strategy=Magnet2026.0620.1
UniformUpdate rule=Linear2026.0624
PPO-EMAgPolicy selection strategy=Magnet2026.0624.9
PPO-EMAgPolicy selection strategy=Last Iterate2026.0627.5
PPO-EMAgPolicy selection strategy=Last Iterate2026.0628.1
UniformUpdate rule=Power Law2026.0631.1
PPO-EMAgPolicy selection strategy=Last Iterate2026.0631.4
UniformUpdate rule=Linear2026.0633.8
UniformUpdate rule=Linear2026.0636.7
UniformUpdate rule=Power Law2026.0643.6
UniformUpdate rule=Power Law2026.0650