Atari Games On Atari 2600 Krull
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| improving-computational-efficiency-in-visual | 3277.5 |
| gdi-rethinking-what-makes-reinforcement | 97575 |
| value-prediction-network | 15930 |
| prioritized-experience-replay | 6872.8 |
| noisy-networks-for-exploration | 10754 |
| massively-parallel-methods-for-deep | 6363.1 |
| dueling-network-architectures-for-deep | 10374.4 |
| evolving-simple-programs-for-playing-atari | 9086.8 |
| deep-reinforcement-learning-with-double-q | 7658.6 |
| asynchronous-methods-for-deep-reinforcement | 5560.0 |
| dueling-network-architectures-for-deep | 8051.6 |
| dueling-network-architectures-for-deep | 11451.9 |
| the-arcade-learning-environment-an-evaluation | 3371.5 |
| mastering-atari-with-discrete-world-models-1 | 50061 |
| increasing-the-action-gap-new-operators-for | 8689.81 |
| asynchronous-methods-for-deep-reinforcement | 5911.4 |
| deep-reinforcement-learning-with-double-q | 8422.3 |
| generalized-data-distribution-iteration | 594540 |
| train-a-real-world-local-path-planner-in-one | 10422.5 |
| mastering-atari-go-chess-and-shogi-by | 269358.27 |
| the-arcade-learning-environment-an-evaluation | 5037 |
| impala-scalable-distributed-deep-rl-with | 8147.40 |
| deep-reinforcement-learning-with-double-q | 6796.1 |
| distributed-prioritized-experience-replay | 11741.4 |
| curl-contrastive-unsupervised-representations | 3833.6 |
| policy-optimization-with-penalized-point | 7715.68 |
| self-imitation-learning | 10614.6 |
| prioritized-experience-replay | 9728.0 |
| recurrent-experience-replay-in-distributed | 218448.1 |
| generalized-data-distribution-iteration | 97575 |
| online-and-offline-reinforcement-learning-by | 72570.5 |
| dna-proximal-policy-optimization-with-a-dual | 10956 |
| Modèle 33 | 3341.0 |
| learning-values-across-many-orders-of | 9745.1 |
| increasing-the-action-gap-new-operators-for | 9548.92 |
| implicit-quantile-networks-for-distributional | 10707 |
| distributional-reinforcement-learning-with-1 | 11447 |
| evolution-strategies-as-a-scalable | 8647.2 |
| asynchronous-methods-for-deep-reinforcement | 8066.6 |
| agent57-outperforming-the-atari-human | 251997.31 |
| deep-exploration-via-bootstrapped-dqn | 8627.9 |
| human-level-control-through-deep | 3805.0 |
| deep-reinforcement-learning-with-double-q | 6206.0 |
| a-distributional-perspective-on-reinforcement | 9735.0 |
| dueling-network-architectures-for-deep | 7920.5 |