Atari Games On Atari 2600 Defender
Métriques
Score
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Score |
|---|---|
| impala-scalable-distributed-deep-rl-with | 185203.00 |
| dueling-network-architectures-for-deep | 41324.5 |
| dueling-network-architectures-for-deep | 42214.0 |
| dueling-network-architectures-for-deep | 34415.0 |
| train-a-real-world-local-path-planner-in-one | 37026.5 |
| generalized-data-distribution-iteration | 970540 |
| increasing-the-action-gap-new-operators-for | 30643.59 |
| distributional-reinforcement-learning-with-1 | 47887 |
| dna-proximal-policy-optimization-with-a-dual | 152768 |
| increasing-the-action-gap-new-operators-for | 32038.93 |
| mastering-atari-go-chess-and-shogi-by | 839642.95 |
| distributed-prioritized-experience-replay | 411943.5 |
| recurrent-experience-replay-in-distributed | 665792.0 |
| evolving-simple-programs-for-playing-atari | 993010 |
| online-and-offline-reinforcement-learning-by | 557200.75 |
| gdi-rethinking-what-makes-reinforcement | 893110 |
| noisy-networks-for-exploration | 42253 |
| generalized-data-distribution-iteration | 893110 |
| implicit-quantile-networks-for-distributional | 53537 |
| the-reactor-a-fast-and-sample-efficient-actor | 223025.0 |
| agent57-outperforming-the-atari-human | 677642.78 |