Competitive Game Strategy Optimization on RPS 1000D
0.0011Final KL DivergencePSRO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| PSROEval. Budget=2e7, Final Target l=-0.0002025.06 | 0.0011 | -0.012 | |
| MGM-E-NESEval. Budget=2e7, Final Target l=-0.0002025.06 | 0.0108 | -0.0004 | |
| OGDAEval. Budget=2e7, Final Target l=-0.0002025.06 | 0.0112 | -0 | |
| LOLAEval. Budget=2e7, Final Target l=-0.0002025.06 | 0.0112 | 0 | |
| PureNESEval. Budget=2e7, Final Target l=-0.0002025.06 | 0.0114 | 0.0002 | |
| DPGEval. Budget=2e7, Final Target l=-0.0002025.06 | 0.014 | 0 | |
| FPEval. Budget=2e7, Final Target l=-0.0002025.06 | 5.97 | 5.97 |