Atari Games On Atari 2600 Star Gunner
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| prioritized-experience-replay | 63302.0 |
| deep-exploration-via-bootstrapped-dqn | 55725 |
| massively-parallel-methods-for-deep | 14919.2 |
| gdi-rethinking-what-makes-reinforcement | 465750 |
| human-level-control-through-deep | 9.4 |
| increasing-the-action-gap-new-operators-for | 61353.59 |
| policy-optimization-with-penalized-point | 48984 |
| dueling-network-architectures-for-deep | 125117.0 |
| generalized-data-distribution-iteration | 677590 |
| asynchronous-methods-for-deep-reinforcement | 64393.0 |
| a-distributional-perspective-on-reinforcement | 49095.0 |
| human-level-control-through-deep | 57997.0 |
| prioritized-experience-replay | 61582.0 |
| mastering-atari-with-discrete-world-models-1 | 7800 |
| recurrent-experience-replay-in-distributed | 717344.0 |
| dueling-network-architectures-for-deep | 89238.0 |
| learning-values-across-many-orders-of | 589.0 |
| evolving-simple-programs-for-playing-atari | 2320 |
| noisy-networks-for-exploration | 75867 |
| self-imitation-learning | 31309.2 |
| fully-parameterized-quantile-function-for | 131981.2 |
| deep-reinforcement-learning-with-double-q | 58365.0 |
| deep-reinforcement-learning-with-double-q | 54282.0 |
| train-a-real-world-local-path-planner-in-one | 129140 |
| impala-scalable-distributed-deep-rl-with | 200625.00 |
| dueling-network-architectures-for-deep | 90804.0 |
| dna-proximal-policy-optimization-with-a-dual | 104125 |
| generalized-data-distribution-iteration | 465750 |
| distributional-reinforcement-learning-with-1 | 77495 |
| dueling-network-architectures-for-deep | 60142.0 |
| mastering-atari-go-chess-and-shogi-by | 549271.70 |
| agent57-outperforming-the-atari-human | 839573.53 |
| the-arcade-learning-environment-an-evaluation | 1345 |
| Modèle 34 | 70000 |
| evolution-strategies-as-a-scalable | 1470.0 |
| deep-reinforcement-learning-with-double-q | 52970.0 |
| the-arcade-learning-environment-an-evaluation | 1069.5 |
| deep-reinforcement-learning-with-double-q | 127073.0 |
| asynchronous-methods-for-deep-reinforcement | 164766.0 |
| asynchronous-methods-for-deep-reinforcement | 138218.0 |
| implicit-quantile-networks-for-distributional | 74677 |
| distributed-prioritized-experience-replay | 434342.5 |
| online-and-offline-reinforcement-learning-by | 154548.26 |