Atari Games On Atari 2600 Surround
評価指標
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
比較表
| モデル名 | Score |
|---|---|
| online-and-offline-reinforcement-learning-by | 9.9 |
| agent57-outperforming-the-atari-human | 9.5 |
| dna-proximal-policy-optimization-with-a-dual | 5.3 |
| increasing-the-action-gap-new-operators-for | 0.72 |
| generalized-data-distribution-iteration | 2.606 |
| impala-scalable-distributed-deep-rl-with | 7.56 |
| noisy-networks-for-exploration | 10 |
| generalized-data-distribution-iteration | -7.8 |
| distributed-prioritized-experience-replay | 7.1 |
| distributional-reinforcement-learning-with-1 | 8.2 |
| train-a-real-world-local-path-planner-in-one | 2.5 |
| recurrent-experience-replay-in-distributed | 9.9 |
| implicit-quantile-networks-for-distributional | 9.4 |
| mastering-atari-go-chess-and-shogi-by | 9.99 |
| gdi-rethinking-what-makes-reinforcement | -7.8 |