Atari Games On Atari 2600 Demon Attack
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 | 143838.04 |
| massively-parallel-methods-for-deep | 14880.1 |
| asynchronous-methods-for-deep-reinforcement | 84997.5 |
| evolution-strategies-as-a-scalable | 1166.5 |
| agent57-outperforming-the-atari-human | 143161.44 |
| dueling-network-architectures-for-deep | 72878.6 |
| the-reactor-a-fast-and-sample-efficient-actor | 115154.0 |
| prioritized-experience-replay | 71846.4 |
| generalized-data-distribution-iteration | 787985 |
| the-arcade-learning-environment-an-evaluation | 28158.8 |
| asynchronous-methods-for-deep-reinforcement | 115201.9 |
| dna-proximal-policy-optimization-with-a-dual | 97909 |
| モデル 13 | 0.0 |
| deep-exploration-via-bootstrapped-dqn | 82610 |
| dueling-network-architectures-for-deep | 60813.3 |
| deep-reinforcement-learning-with-double-q | 12550.7 |
| increasing-the-action-gap-new-operators-for | 70908.17 |
| the-arcade-learning-environment-an-evaluation | 520.5 |
| self-imitation-learning | 10140.5 |
| mastering-atari-go-chess-and-shogi-by | 143964.26 |
| playing-atari-with-six-neurons | 325 |
| recurrent-experience-replay-in-distributed | 140002.3 |
| increasing-the-action-gap-new-operators-for | 27153.48 |
| learning-values-across-many-orders-of | 63644.9 |
| deep-reinforcement-learning-with-double-q | 12149.4 |
| mastering-atari-with-discrete-world-models-1 | 82263 |
| generalized-data-distribution-iteration | 675530 |
| impala-scalable-distributed-deep-rl-with | 132826.98 |
| policy-optimization-with-penalized-point | 61147.33 |
| implicit-quantile-networks-for-distributional | 128580 |
| distributed-prioritized-experience-replay | 133086.4 |
| human-level-control-through-deep | 9711.0 |
| prioritized-experience-replay | 61277.5 |
| gdi-rethinking-what-makes-reinforcement | 675530 |
| dueling-network-architectures-for-deep | 56322.8 |
| dueling-network-architectures-for-deep | 58044.2 |
| evolving-simple-programs-for-playing-atari | 2387 |
| distributional-reinforcement-learning-with-1 | 121551 |
| noisy-networks-for-exploration | 69311 |
| deep-reinforcement-learning-with-double-q | 69803.4 |
| a-distributional-perspective-on-reinforcement | 130955.0 |
| モデル 42 | 230324 |
| train-a-real-world-local-path-planner-in-one | 119773.9 |
| deep-reinforcement-learning-with-double-q | 73371.3 |
| curl-contrastive-unsupervised-representations | 834 |
| asynchronous-methods-for-deep-reinforcement | 113308.4 |