Game Playing on Goofspiel Standard Benchmarks (test)
0.007ExploitabilityPPO-EMAg
Evaluation Results
| Method | Links | |
|---|---|---|
| PPO-EMAgPolicy selection strategy=Magnet2026.06 | 0.007 | |
| PPO-EMAgPolicy selection strategy=Last Iterate2026.06 | 0.015 | |
| PPO-EMAgPolicy selection strategy=Magnet2026.06 | 0.017 | |
| PPO-EMAgPolicy selection strategy=Last Iterate2026.06 | 0.021 | |
| UniformUpdate rule=Linear2026.06 | 0.03 | |
| UniformUpdate rule=Linear2026.06 | 0.031 | |
| UniformUpdate rule=Power Law2026.06 | 0.033 | |
| UniformUpdate rule=Power Law2026.06 | 0.037 |