Two-Player Zero-Sum Game Solving on Goofspiel 13 cards
73.9Estimated PEPSD-PSRO w/ PRD
Evaluation Results
| Method | Links | |
|---|---|---|
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=19.22026.05 | 73.9 | |
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=38.42026.05 | 67.7 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=19.22026.05 | 67 | |
| PSRO w/ PRDEnvironment steps (x10^6)=19.22026.05 | 66.7 | |
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=57.62026.05 | 61.6 | |
| PSD-PSRO w/ AlphaRankEnvironment steps (x10^6)=19.22026.05 | 59.9 | |
| PSRO w/ NashEnvironment steps (x10^6)=19.22026.05 | 57.9 | |
| PSRO w/ PRDEnvironment steps (x10^6)=38.42026.05 | 56.9 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=19.22026.05 | 56.3 | |
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=76.82026.05 | 56.2 | |
| PSD-PSRO w/ UniformEnvironment steps (x10^6)=19.22026.05 | 55.4 | |
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=96.02026.05 | 53.3 | |
| PSRO w/ PRDEnvironment steps (x10^6)=57.62026.05 | 53.1 | |
| PSRO w/ UniformEnvironment steps (x10^6)=19.22026.05 | 50 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=38.42026.05 | 50 | |
| PSRO w/ PRDEnvironment steps (x10^6)=76.82026.05 | 49.8 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=38.42026.05 | 49.4 | |
| PSRO w/ PRDEnvironment steps (x10^6)=96.02026.05 | 47.9 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=57.62026.05 | 47.4 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=19.22026.05 | 45.9 | |
| PSRO w/ PRDEnvironment steps (x10^6)=115.22026.05 | 44.9 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=76.82026.05 | 44.3 | |
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=115.22026.05 | 43.7 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=96.02026.05 | 43.1 | |
| PSRO w/ NashEnvironment steps (x10^6)=38.42026.05 | 41.1 | |
| PSRO w/ PRDEnvironment steps (x10^6)=134.42026.05 | 40.4 | |
| Anytime PSROEnvironment steps (x10^6)=19.22026.05 | 40.4 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=57.62026.05 | 39.6 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=19.22026.05 | 39 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=115.22026.05 | 37.2 | |
| PSRO w/ UniformEnvironment steps (x10^6)=38.42026.05 | 36.9 | |
| PSRO w/ PRDEnvironment steps (x10^6)=153.62026.05 | 36.6 | |
| PSD-PSRO w/ AlphaRankEnvironment steps (x10^6)=38.42026.05 | 34.9 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=134.42026.05 | 34.5 | |
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=134.42026.05 | 34.5 | |
| PSD-PSRO w/ UniformEnvironment steps (x10^6)=38.42026.05 | 34.1 | |
| NeuPL w/ NashEnvironment steps (x10^6)=19.22026.05 | 33.7 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=76.82026.05 | 33.5 | |
| NeuPL w/ PRDEnvironment steps (x10^6)=153.62026.05 | 33.4 | |
| PSD-PSRO w/ UniformEnvironment steps (x10^6)=57.62026.05 | 32.8 | |
| PSRO w/ UniformEnvironment steps (x10^6)=57.62026.05 | 32.7 | |
| PSRO w/ NashEnvironment steps (x10^6)=57.62026.05 | 32.1 | |
| PSD-PSRO w/ PRDEnvironment steps (x10^6)=153.62026.05 | 30.9 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=96.02026.05 | 30.6 | |
| Global PSROEnvironment steps (x10^6)=19.22026.05 | 30.5 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=38.42026.05 | 30.1 | |
| NeuPL w/ NashEnvironment steps (x10^6)=38.42026.05 | 29.8 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=38.42026.05 | 29.2 | |
| PSRO w/ NashEnvironment steps (x10^6)=76.82026.05 | 28.4 | |
| PSD-PSRO w/ AlphaRankEnvironment steps (x10^6)=57.62026.05 | 28.4 | |
| PSRO w/ UniformEnvironment steps (x10^6)=96.02026.05 | 28.2 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=115.22026.05 | 28.2 | |
| PSD-PSRO w/ UniformEnvironment steps (x10^6)=76.82026.05 | 28.1 | |
| PSRO w/ UniformEnvironment steps (x10^6)=76.82026.05 | 27.7 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=57.62026.05 | 27.3 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=134.42026.05 | 25.8 | |
| PSD-PSRO w/ UniformEnvironment steps (x10^6)=96.02026.05 | 25.6 | |
| PSRO w/ UniformEnvironment steps (x10^6)=134.42026.05 | 25.4 | |
| PSRO w/ NashEnvironment steps (x10^6)=96.02026.05 | 25.1 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=76.82026.05 | 25.1 | |
| PSD-PSRO w/ AlphaRankEnvironment steps (x10^6)=76.82026.05 | 25.1 | |
| PSD-PSRO w/ AlphaRankEnvironment steps (x10^6)=96.02026.05 | 24.9 | |
| NeuPL w/ AlphaRankEnvironment steps (x10^6)=19.22026.05 | 24.4 | |
| PSD-PSRO w/ UniformEnvironment steps (x10^6)=115.22026.05 | 23.9 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=96.02026.05 | 23.5 | |
| NeuPL w/ NashEnvironment steps (x10^6)=57.62026.05 | 23.4 | |
| PSRO w/ UniformEnvironment steps (x10^6)=153.62026.05 | 23 | |
| NeuPL w/ NashEnvironment steps (x10^6)=76.82026.05 | 22.5 | |
| Anytime PSROEnvironment steps (x10^6)=38.42026.05 | 22.3 | |
| Anytime PSROEnvironment steps (x10^6)=76.82026.05 | 22.3 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=57.62026.05 | 22.1 | |
| PSD-PSRO w/ AlphaRankEnvironment steps (x10^6)=115.22026.05 | 22 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=134.42026.05 | 21.9 | |
| Anytime PSROEnvironment steps (x10^6)=57.62026.05 | 21.8 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=115.22026.05 | 21.5 | |
| NeuPL w/ AlphaRankEnvironment steps (x10^6)=38.42026.05 | 21.2 | |
| PSD-PSRO w/ AlphaRankEnvironment steps (x10^6)=134.42026.05 | 21.2 | |
| PSD-PSRO w/ NashEnvironment steps (x10^6)=153.62026.05 | 21.1 | |
| NeuPL w/ AlphaRankEnvironment steps (x10^6)=57.62026.05 | 20.9 | |
| PSRO w/ NashEnvironment steps (x10^6)=115.22026.05 | 20.6 | |
| Anytime PSROEnvironment steps (x10^6)=96.02026.05 | 20.3 | |
| Anytime PSROEnvironment steps (x10^6)=134.42026.05 | 20.3 | |
| PSD-PSRO w/ UniformEnvironment steps (x10^6)=134.42026.05 | 20.3 | |
| PSRO w/ UniformEnvironment steps (x10^6)=115.22026.05 | 20 | |
| PSRO w/ NashEnvironment steps (x10^6)=153.62026.05 | 19.3 | |
| Anytime PSROEnvironment steps (x10^6)=153.62026.05 | 19.1 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=134.42026.05 | 19 | |
| PSRO w/ NashEnvironment steps (x10^6)=134.42026.05 | 18.8 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=76.82026.05 | 18.8 | |
| NeuPL w/ AlphaRankEnvironment steps (x10^6)=115.22026.05 | 18.7 | |
| Anytime PSROEnvironment steps (x10^6)=115.22026.05 | 18.3 | |
| NeuPL w/ AlphaRankEnvironment steps (x10^6)=96.02026.05 | 18.3 | |
| NeuPL w/ NashEnvironment steps (x10^6)=96.02026.05 | 18.2 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=153.62026.05 | 17.8 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=96.02026.05 | 17 | |
| NeuPL w/ UniformEnvironment steps (x10^6)=153.62026.05 | 17 | |
| NeuPL w/ NashEnvironment steps (x10^6)=134.42026.05 | 16.9 | |
| NeuPL w/ AlphaRankEnvironment steps (x10^6)=76.82026.05 | 16.9 | |
| PSRO w/ AlphaRankEnvironment steps (x10^6)=115.22026.05 | 16.2 | |
| NeuPL w/ NashEnvironment steps (x10^6)=115.22026.05 | 16.2 |