Atari Games On Atari 2600 Phoenix
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 |
|---|---|
| impala-scalable-distributed-deep-rl-with | 210996.45 |
| increasing-the-action-gap-new-operators-for | 22038.27 |
| mastering-atari-go-chess-and-shogi-by | 955137.84 |
| fully-parameterized-quantile-function-for | 174077.5 |
| distributional-reinforcement-learning-with-1 | 16585 |
| generalized-data-distribution-iteration | 894460 |
| train-a-real-world-local-path-planner-in-one | 71752.6 |
| recurrent-experience-replay-in-distributed | 864020.0 |
| dna-proximal-policy-optimization-with-a-dual | 391085 |
| gdi-rethinking-what-makes-reinforcement | 894460 |
| dueling-network-architectures-for-deep | 63597.0 |
| implicit-quantile-networks-for-distributional | 56599 |
| agent57-outperforming-the-atari-human | 908264.15 |
| distributed-prioritized-experience-replay | 224491.1 |
| increasing-the-action-gap-new-operators-for | 14495.56 |
| generalized-data-distribution-iteration | 959580 |
| noisy-networks-for-exploration | 10379 |
| online-and-offline-reinforcement-learning-by | 815728.7 |
| mastering-atari-with-discrete-world-models-1 | 49375 |
| evolving-simple-programs-for-playing-atari | 7520 |
| playing-atari-with-six-neurons | 4600 |