Atari Games On Atari 2600 Hero
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| fully-parameterized-quantile-function-for | 30926.2 |
| deep-reinforcement-learning-with-double-q | 20437.8 |
| human-level-control-through-deep | 19950 |
| deep-reinforcement-learning-with-double-q | 15459.2 |
| evolving-simple-programs-for-playing-atari | 2974 |
| self-imitation-learning | 33156.7 |
| dueling-network-architectures-for-deep | 21036.5 |
| distributed-prioritized-experience-replay | 31655.9 |
| massively-parallel-methods-for-deep | 8963.4 |
| dueling-network-architectures-for-deep | 20130.2 |
| asynchronous-methods-for-deep-reinforcement | 32464.1 |
| mastering-atari-with-discrete-world-models-1 | 21868 |
| deep-exploration-via-bootstrapped-dqn | 21021.3 |
| online-and-offline-reinforcement-learning-by | 37234.31 |
| asynchronous-methods-for-deep-reinforcement | 28889.5 |
| the-arcade-learning-environment-an-evaluation | 12859.5 |
| prioritized-experience-replay | 20889.9 |
| dueling-network-architectures-for-deep | 15207.9 |
| generalized-data-distribution-iteration | 38330 |
| increasing-the-action-gap-new-operators-for | 24175.79 |
| noisy-networks-for-exploration | 31533 |
| increasing-the-action-gap-new-operators-for | 24788.86 |
| asynchronous-methods-for-deep-reinforcement | 28765.8 |
| agent57-outperforming-the-atari-human | 114736.26 |
| mastering-atari-go-chess-and-shogi-by | 49244.11 |
| gdi-rethinking-what-makes-reinforcement | 38330 |
| the-arcade-learning-environment-an-evaluation | 6459 |
| Modèle 28 | 7295 |
| recurrent-experience-replay-in-distributed | 39537.1 |
| deep-reinforcement-learning-with-double-q | 14992.9 |
| impala-scalable-distributed-deep-rl-with | 33730.55 |
| distributional-reinforcement-learning-with-1 | 21395 |
| curl-contrastive-unsupervised-representations | 6235.1 |
| a-distributional-perspective-on-reinforcement | 38874 |
| the-arcade-learning-environment-an-evaluation | 6458.8 |
| learning-values-across-many-orders-of | 14225.2 |
| model-free-episodic-control-with-state | 11732 |
| dna-proximal-policy-optimization-with-a-dual | 24904 |
| generalized-data-distribution-iteration | 38225 |
| deep-reinforcement-learning-with-double-q | 14892.5 |
| prioritized-experience-replay | 23037.7 |
| implicit-quantile-networks-for-distributional | 28386 |
| dueling-network-architectures-for-deep | 20818.2 |
| train-a-real-world-local-path-planner-in-one | 26578.5 |