Atari Games On Atari 2600 Name This Game
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| dueling-network-architectures-for-deep | 11185.1 |
| evolution-strategies-as-a-scalable | 4503.0 |
| deep-exploration-via-bootstrapped-dqn | 11501.1 |
| dueling-network-architectures-for-deep | 15572.5 |
| generalized-data-distribution-iteration | 36296 |
| self-imitation-learning | 14958.2 |
| deep-reinforcement-learning-with-double-q | 8207.8 |
| impala-scalable-distributed-deep-rl-with | 21537.20 |
| human-level-control-through-deep | 7257.0 |
| distributional-reinforcement-learning-with-1 | 21890 |
| Modèle 11 | 2247.0 |
| deep-reinforcement-learning-with-double-q | 13637.9 |
| generalized-data-distribution-iteration | 34434 |
| a-distributional-perspective-on-reinforcement | 12542.0 |
| train-a-real-world-local-path-planner-in-one | 16535.4 |
| deep-reinforcement-learning-with-double-q | 8960.3 |
| asynchronous-methods-for-deep-reinforcement | 12093.7 |
| noisy-networks-for-exploration | 12211 |
| mastering-atari-go-chess-and-shogi-by | 157177.85 |
| asynchronous-methods-for-deep-reinforcement | 10476.1 |
| learning-values-across-many-orders-of | 15851.2 |
| recurrent-experience-replay-in-distributed | 58182.7 |
| prioritized-experience-replay | 10497.6 |
| increasing-the-action-gap-new-operators-for | 10431.33 |
| prioritized-experience-replay | 12270.5 |
| mastering-atari-with-discrete-world-models-1 | 14649 |
| agent57-outperforming-the-atari-human | 54386.77 |
| dueling-network-architectures-for-deep | 11971.1 |
| dna-proximal-policy-optimization-with-a-dual | 20226 |
| implicit-quantile-networks-for-distributional | 22682 |
| the-arcade-learning-environment-an-evaluation | 15410 |
| policy-optimization-with-penalized-point | 6065.63 |
| dueling-network-architectures-for-deep | 10616.0 |
| online-and-offline-reinforcement-learning-by | 101197.71 |
| playing-atari-with-six-neurons | 920 |
| deep-reinforcement-learning-with-double-q | 6738.8 |
| evolving-simple-programs-for-playing-atari | 3696 |
| asynchronous-methods-for-deep-reinforcement | 5614.0 |
| distributed-prioritized-experience-replay | 25783.3 |
| increasing-the-action-gap-new-operators-for | 11025.26 |
| massively-parallel-methods-for-deep | 9238.5 |
| gdi-rethinking-what-makes-reinforcement | 34434 |
| the-arcade-learning-environment-an-evaluation | 2500.1 |