Atari Games On Atari 2600 Zaxxon
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| the-arcade-learning-environment-an-evaluation | 3365.1 |
| deep-reinforcement-learning-with-double-q | 4412.0 |
| mastering-atari-with-discrete-world-models-1 | 50699 |
| noisy-networks-for-exploration | 14874 |
| implicit-quantile-networks-for-distributional | 21772 |
| recurrent-independent-mechanisms | 15000 |
| learning-values-across-many-orders-of | 14402.0 |
| dna-proximal-policy-optimization-with-a-dual | 22588 |
| distributional-reinforcement-learning-with-1 | 13112 |
| dueling-network-architectures-for-deep | 13886.0 |
| agent57-outperforming-the-atari-human | 249808.9 |
| generalized-data-distribution-iteration | 216020 |
| online-and-offline-reinforcement-learning-by | 154131.86 |
| generalized-data-distribution-iteration | 109140 |
| impala-scalable-distributed-deep-rl-with | 32935.50 |
| massively-parallel-methods-for-deep | 6159.4 |
| prioritized-experience-replay | 9474.0 |
| asynchronous-methods-for-deep-reinforcement | 2659.0 |
| policy-optimization-with-penalized-point | 9472 |
| increasing-the-action-gap-new-operators-for | 9129.61 |
| evolution-strategies-as-a-scalable | 6380.0 |
| dueling-network-architectures-for-deep | 10163.0 |
| asynchronous-methods-for-deep-reinforcement | 24622.0 |
| a-distributional-perspective-on-reinforcement | 10513.0 |
| deep-reinforcement-learning-with-double-q | 11320.0 |
| distributed-prioritized-experience-replay | 42285.5 |
| human-level-control-through-deep | 4977.0 |
| self-imitation-learning | 9164.2 |
| asynchronous-methods-for-deep-reinforcement | 23519.0 |
| Modèle 30 | 21.4 |
| train-a-real-world-local-path-planner-in-one | 16420 |
| prioritized-experience-replay | 10469.0 |
| deep-reinforcement-learning-with-double-q | 8593.0 |
| the-arcade-learning-environment-an-evaluation | 22610 |
| mastering-atari-go-chess-and-shogi-by | 725853.90 |
| dueling-network-architectures-for-deep | 12944.0 |
| deep-reinforcement-learning-with-double-q | 5363.0 |
| recurrent-experience-replay-in-distributed | 224910.7 |
| evolving-simple-programs-for-playing-atari | 2980 |
| deep-exploration-via-bootstrapped-dqn | 11491.7 |
| dueling-network-architectures-for-deep | 10164.0 |