Atari Games On Atari 2600 Atlantis
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| implicit-quantile-networks-for-distributional | 978200 |
| a-distributional-perspective-on-reinforcement | 841075.0 |
| dueling-network-architectures-for-deep | 106056.0 |
| dueling-network-architectures-for-deep | 382572.0 |
| noisy-networks-for-exploration | 972175 |
| distributed-prioritized-experience-replay | 944497.5 |
| prioritized-experience-replay | 357324.0 |
| generalized-data-distribution-iteration | 3803000 |
| increasing-the-action-gap-new-operators-for | 1465250 |
| the-arcade-learning-environment-an-evaluation | 193858 |
| deep-exploration-via-bootstrapped-dqn | 994500 |
| train-a-real-world-local-path-planner-in-one | 947275 |
| asynchronous-methods-for-deep-reinforcement | 875822.0 |
| distributional-reinforcement-learning-with-1 | 971850 |
| evolution-strategies-as-a-scalable | 1267410.0 |
| human-level-control-through-deep | 85641.0 |
| increasing-the-action-gap-new-operators-for | 553591.67 |
| deep-reinforcement-learning-with-double-q | 319688.0 |
| agent57-outperforming-the-atari-human | 1528841.76 |
| policy-optimization-with-penalized-point | 2193605.67 |
| dueling-network-architectures-for-deep | 445360.0 |
| learning-values-across-many-orders-of | 340076.0 |
| deep-reinforcement-learning-with-double-q | 292491.0 |
| dna-proximal-policy-optimization-with-a-dual | 932559 |
| the-arcade-learning-environment-an-evaluation | 62687 |
| mastering-atari-go-chess-and-shogi-by | 1674767.20 |
| asynchronous-methods-for-deep-reinforcement | 911091.0 |
| Modèle 28 | 852.9 |
| dueling-network-architectures-for-deep | 395762.0 |
| mastering-atari-with-discrete-world-models-1 | 978778 |
| prioritized-experience-replay | 330647.0 |
| self-imitation-learning | 3084781.7 |
| the-reactor-a-fast-and-sample-efficient-actor | 302831.0 |
| massively-parallel-methods-for-deep | 629166.5 |
| recurrent-experience-replay-in-distributed | 1620764.0 |
| evolving-simple-programs-for-playing-atari | 99240 |
| generalized-data-distribution-iteration | 3837300 |
| online-and-offline-reinforcement-learning-by | 1137475.12 |
| deep-reinforcement-learning-with-double-q | 279987.0 |
| asynchronous-methods-for-deep-reinforcement | 772392.0 |
| deep-reinforcement-learning-with-double-q | 423252.0 |
| impala-scalable-distributed-deep-rl-with | 849967.50 |