Atari Games On Atari 2600 Boxing
Metriken
Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Score |
|---|---|
| asynchronous-methods-for-deep-reinforcement | 37.3 |
| Modell 2 | 9.8 |
| online-and-offline-reinforcement-learning-by | 100 |
| gdi-rethinking-what-makes-reinforcement | 100 |
| the-reactor-a-fast-and-sample-efficient-actor | 99.4 |
| asynchronous-methods-for-deep-reinforcement | 59.8 |
| the-arcade-learning-environment-an-evaluation | 100 |
| train-a-real-world-local-path-planner-in-one | 99.6 |
| self-imitation-learning | 99.6 |
| agent57-outperforming-the-atari-human | 100 |
| dueling-network-architectures-for-deep | 91.6 |
| generalized-data-distribution-iteration | 100 |
| curl-contrastive-unsupervised-representations | 4.8 |
| dna-proximal-policy-optimization-with-a-dual | 99.9 |
| the-arcade-learning-environment-an-evaluation | 44 |
| distributed-prioritized-experience-replay | 100 |
| mastering-atari-with-discrete-world-models-1 | 92 |
| dueling-network-architectures-for-deep | 99.4 |
| deep-reinforcement-learning-with-double-q | 70.3 |
| implicit-quantile-networks-for-distributional | 99.8 |
| prioritized-experience-replay | 95.6 |
| increasing-the-action-gap-new-operators-for | 94.3 |
| prioritized-experience-replay | 72.3 |
| massively-parallel-methods-for-deep | 74.2 |
| deep-reinforcement-learning-with-double-q | 73.5 |
| dueling-network-architectures-for-deep | 77.3 |
| recurrent-experience-replay-in-distributed | 98.5 |
| deep-exploration-via-bootstrapped-dqn | 93.2 |
| distributed-deep-reinforcement-learning-learn | 98 |
| human-level-control-through-deep | 71.8 |
| learning-values-across-many-orders-of | 99.3 |
| distributional-reinforcement-learning-with-1 | 99.9 |
| a-distributional-perspective-on-reinforcement | 97.8 |
| policy-optimization-with-penalized-point | 97.23 |
| deep-reinforcement-learning-with-double-q | 79.2 |
| dueling-network-architectures-for-deep | 98.9 |
| noisy-networks-for-exploration | 100 |
| mastering-atari-go-chess-and-shogi-by | 100.00 |
| deep-reinforcement-learning-with-double-q | 88.0 |
| increasing-the-action-gap-new-operators-for | 93.94 |
| evolving-simple-programs-for-playing-atari | 38.4 |
| generalized-data-distribution-iteration | 100 |
| impala-scalable-distributed-deep-rl-with | 99.96 |
| evolution-strategies-as-a-scalable | 49.8 |
| asynchronous-methods-for-deep-reinforcement | 33.7 |