Atari Games On Atari 2600 Seaquest
المقاييس
Score
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | Score |
|---|---|
| playing-atari-with-deep-reinforcement | 1740 |
| soft-actor-critic-for-discrete-action | 211.6 |
| mastering-atari-go-chess-and-shogi-by | 999976.52 |
| deep-reinforcement-learning-with-double-q | 4216.7 |
| asynchronous-methods-for-deep-reinforcement | 2300.2 |
| a-distributional-perspective-on-reinforcement | 266434.0 |
| prioritized-experience-replay | 26357.8 |
| generalized-data-distribution-iteration | 943910 |
| prioritized-experience-replay | 25463.7 |
| self-imitation-learning | 2456.5 |
| dna-proximal-policy-optimization-with-a-dual | 4146 |
| deep-reinforcement-learning-with-double-q | 14498.0 |
| evolution-strategies-as-a-scalable | 1390.0 |
| recurrent-rational-networks | 7460 |
| discrete-latent-space-world-models-for | 635 |
| gdi-rethinking-what-makes-reinforcement | 943910 |
| dueling-network-architectures-for-deep | 37361.6 |
| deep-exploration-via-bootstrapped-dqn | 9083.1 |
| human-level-control-through-deep | 5286.0 |
| mean-actor-critic | 1703.4 |
| the-arcade-learning-environment-an-evaluation | 5132.4 |
| agent57-outperforming-the-atari-human | 999997.63 |
| curl-contrastive-unsupervised-representations | 408 |
| recurrent-rational-networks | 6603 |
| noisy-networks-for-exploration | 16754 |
| playing-atari-with-six-neurons | 320 |
| distributed-deep-reinforcement-learning-learn | 1832 |
| increasing-the-action-gap-new-operators-for | 8670.5 |
| dueling-network-architectures-for-deep | 16452.7 |
| deep-attention-recurrent-q-network | 7263 |
| the-arcade-learning-environment-an-evaluation | 664.8 |
| dueling-network-architectures-for-deep | 931.6 |
| iq-learn-inverse-soft-q-learning-for | - |
| increasing-the-action-gap-new-operators-for | 13230.74 |
| implicit-quantile-networks-for-distributional | 30140 |
| value-prediction-network | 5628 |
| النموذج 37 | 675.5 |
| generalized-data-distribution-iteration | 1000000 |
| deep-reinforcement-learning-with-double-q | 5860.6 |
| mastering-atari-with-discrete-world-models-1 | 7480 |
| train-a-real-world-local-path-planner-in-one | 29278.6 |
| dueling-network-architectures-for-deep | 50254.2 |
| evolving-simple-programs-for-playing-atari | 724 |
| decision-transformer-reinforcement-learning | 2.4 |
| generalized-data-distribution-iteration | 1000000 |
| asynchronous-methods-for-deep-reinforcement | 1326.1 |
| improving-computational-efficiency-in-visual | 561.2 |
| impala-scalable-distributed-deep-rl-with | 1753.20 |
| distributional-reinforcement-learning-with-1 | 8268 |
| learning-values-across-many-orders-of | 10932.3 |
| deep-reinforcement-learning-with-double-q | 1431.2 |
| asynchronous-methods-for-deep-reinforcement | 2355.4 |
| policy-optimization-with-penalized-point | 1807.47 |
| massively-parallel-methods-for-deep | 10145.9 |
| online-and-offline-reinforcement-learning-by | 999659.18 |
| recurrent-experience-replay-in-distributed | 999996.7 |
| distributed-prioritized-experience-replay | 392952.3 |