2048 On 2048
評価指標
Average Score
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Average Score | Paper Title | Repository |
|---|---|---|---|
| AlphaZero (With Simulator) | 500000 | Planning in Stochastic Environments with a Learned Model | |
| MuZero | 300000 | Planning in Stochastic Environments with a Learned Model | |
| Beam Search | 1024 | Playing 2048 With Reinforcement Learning | |
| DQN (1000 episodes) | 256 | Playing 2048 With Reinforcement Learning | |
| Stochastic Muzero | 500000 | Planning in Stochastic Environments with a Learned Model |
0 of 5 row(s) selected.