Atari Games On Atari 2600 Breakout
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| implicit-quantile-networks-for-distributional | 734 |
| asynchronous-methods-for-deep-reinforcement | 551.6 |
| the-arcade-learning-environment-an-evaluation | 364.4 |
| optimizing-the-neural-architecture-of | 144.4 |
| fully-parameterized-quantile-function-for | 854.2 |
| deep-exploration-via-bootstrapped-dqn | 855 |
| evolving-simple-programs-for-playing-atari | 13.2 |
| online-and-offline-reinforcement-learning-by | 758.04 |
| agent57-outperforming-the-atari-human | 790.4 |
| optimizing-the-neural-architecture-of | 161.1 |
| the-arcade-learning-environment-an-evaluation | 5.2 |
| train-a-real-world-local-path-planner-in-one | 621.7 |
| policy-optimization-with-penalized-point | 458.41 |
| curl-contrastive-unsupervised-representations | 18.2 |
| deep-reinforcement-learning-with-double-q | 354.6 |
| prioritized-experience-replay | 373.9 |
| human-level-control-through-deep | 401.2 |
| dueling-network-architectures-for-deep | 366.0 |
| decision-transformer-reinforcement-learning | 267.5 |
| playing-atari-with-deep-reinforcement | 225 |
| optimizing-the-neural-architecture-of | 91.4 |
| learning-values-across-many-orders-of | 344.1 |
| noisy-networks-for-exploration | 263 |
| generalized-data-distribution-iteration | 864.00 |
| Modèle 25 | 6.1 |
| generalized-data-distribution-iteration | 864.00 |
| generalized-data-distribution-iteration | 864 |
| increasing-the-action-gap-new-operators-for | 425.32 |
| distributional-reinforcement-learning-with-1 | 742 |
| increasing-the-action-gap-new-operators-for | 431.89 |
| asynchronous-methods-for-deep-reinforcement | 766.8 |
| deep-attention-recurrent-q-network | 20 |
| generalized-data-distribution-iteration | 864.00 |
| recurrent-experience-replay-in-distributed | 837.7 |
| deep-reinforcement-learning-with-double-q | 354.5 |
| prioritized-experience-replay | 343.0 |
| dueling-network-architectures-for-deep | 411.6 |
| distributed-prioritized-experience-replay | 800.9 |
| mean-actor-critic | 372.7 |
| optimizing-the-neural-architecture-of | 180.6 |
| evolution-strategies-as-a-scalable | 9.5 |
| dna-proximal-policy-optimization-with-a-dual | 626 |
| recurrent-rational-networks | 336 |
| impala-scalable-distributed-deep-rl-with | 787.34 |
| the-reactor-a-fast-and-sample-efficient-actor | 514.8 |
| recurrent-rational-networks | 316 |
| discrete-latent-space-world-models-for | 11.6 |
| dueling-network-architectures-for-deep | 345.3 |
| a-distributional-perspective-on-reinforcement | 748.0 |
| asynchronous-methods-for-deep-reinforcement | 681.9 |
| soft-actor-critic-for-discrete-action | 0.7 |
| dueling-network-architectures-for-deep | 418.5 |
| self-imitation-learning | 452 |
| deep-reinforcement-learning-with-double-q | 385.5 |
| distributed-deep-reinforcement-learning-learn | 350 |
| massively-parallel-methods-for-deep | 313.0 |
| deep-reinforcement-learning-with-double-q | 368.9 |
| mastering-atari-with-discrete-world-models-1 | 312 |