Game Playing on Biased RPS Standard (test)
17.9ExploitabilityPPO-EMAg
Evaluation Results
| Method | Links | |
|---|---|---|
| PPO-EMAgPolicy selection strategy=Magnet2026.06 | 17.9 | |
| PPO-EMAgPolicy selection strategy=Magnet2026.06 | 20.1 | |
| UniformUpdate rule=Linear2026.06 | 24 | |
| PPO-EMAgPolicy selection strategy=Magnet2026.06 | 24.9 | |
| PPO-EMAgPolicy selection strategy=Last Iterate2026.06 | 27.5 | |
| PPO-EMAgPolicy selection strategy=Last Iterate2026.06 | 28.1 | |
| UniformUpdate rule=Power Law2026.06 | 31.1 | |
| PPO-EMAgPolicy selection strategy=Last Iterate2026.06 | 31.4 | |
| UniformUpdate rule=Linear2026.06 | 33.8 | |
| UniformUpdate rule=Linear2026.06 | 36.7 | |
| UniformUpdate rule=Power Law2026.06 | 43.6 | |
| UniformUpdate rule=Power Law2026.06 | 50 |