Atari Games On Atari 2600 Fishing Derby
Metriken
Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Score |
|---|---|
| impala-scalable-distributed-deep-rl-with | 44.85 |
| fully-parameterized-quantile-function-for | 52.7 |
| dueling-network-architectures-for-deep | -4.1 |
| learning-values-across-many-orders-of | 45.1 |
| deep-reinforcement-learning-with-double-q | -4.9 |
| policy-optimization-with-penalized-point | 28.99 |
| evolving-simple-programs-for-playing-atari | -51 |
| dueling-network-architectures-for-deep | 46.4 |
| generalized-data-distribution-iteration | 59 |
| noisy-networks-for-exploration | 57 |
| distributional-reinforcement-learning-with-1 | 39 |
| distributed-prioritized-experience-replay | 44.4 |
| increasing-the-action-gap-new-operators-for | 21.32 |
| the-arcade-learning-environment-an-evaluation | -89.5 |
| prioritized-experience-replay | 9.8 |
| mastering-atari-with-discrete-world-models-1 | 65 |
| self-imitation-learning | 55.8 |
| playing-atari-with-six-neurons | -10 |
| recurrent-experience-replay-in-distributed | 85.8 |
| gdi-rethinking-what-makes-reinforcement | 59 |
| generalized-data-distribution-iteration | 65 |
| online-and-offline-reinforcement-learning-by | 73.94 |
| mastering-atari-go-chess-and-shogi-by | 91.16 |
| prioritized-experience-replay | 39.5 |
| a-distributional-perspective-on-reinforcement | 8.9 |
| the-arcade-learning-environment-an-evaluation | 37.8 |
| evolution-strategies-as-a-scalable | -49.0 |
| dna-proximal-policy-optimization-with-a-dual | 57.4 |
| train-a-real-world-local-path-planner-in-one | 35.1 |
| increasing-the-action-gap-new-operators-for | 28.13 |
| dueling-network-architectures-for-deep | 41.3 |
| deep-exploration-via-bootstrapped-dqn | 26 |
| implicit-quantile-networks-for-distributional | 33.8 |
| asynchronous-methods-for-deep-reinforcement | 18.8 |
| deep-reinforcement-learning-with-double-q | 3.2 |
| deep-reinforcement-learning-with-double-q | -1.6 |
| deep-reinforcement-learning-with-double-q | 17.0 |
| asynchronous-methods-for-deep-reinforcement | 22.6 |
| human-level-control-through-deep | -0.8 |
| dueling-network-architectures-for-deep | 15.5 |
| agent57-outperforming-the-atari-human | 86.97 |
| asynchronous-methods-for-deep-reinforcement | 13.6 |
| Modell 43 | -85.1 |
| massively-parallel-methods-for-deep | 4.6 |