Atari Games On Atari 2600 Kung Fu Master
평가 지표
Score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Score |
|---|---|
| prioritized-experience-replay | 39581.0 |
| deep-reinforcement-learning-with-double-q | 20882.0 |
| dueling-network-architectures-for-deep | 29710.0 |
| asynchronous-methods-for-deep-reinforcement | 40835.0 |
| increasing-the-action-gap-new-operators-for | 32182.99 |
| dueling-network-architectures-for-deep | 48375.0 |
| asynchronous-methods-for-deep-reinforcement | 3046.0 |
| generalized-data-distribution-iteration | 140440 |
| fully-parameterized-quantile-function-for | 111138.5 |
| deep-reinforcement-learning-with-double-q | 30207.0 |
| deep-exploration-via-bootstrapped-dqn | 36733.3 |
| learning-values-across-many-orders-of | 34393.0 |
| evolving-simple-programs-for-playing-atari | 57400 |
| policy-optimization-with-penalized-point | 33728 |
| increasing-the-action-gap-new-operators-for | 34650.91 |
| gdi-rethinking-what-makes-reinforcement-1 | 1666000 |
| mastering-atari-with-discrete-world-models-1 | 62741 |
| noisy-networks-for-exploration | 41672 |
| massively-parallel-methods-for-deep | 20620.0 |
| deep-reinforcement-learning-with-double-q | 26059.0 |
| the-arcade-learning-environment-an-evaluation | 48854.5 |
| the-arcade-learning-environment-an-evaluation | 19544 |
| dueling-network-architectures-for-deep | 24288.0 |
| prioritized-experience-replay | 31676.0 |
| train-a-real-world-local-path-planner-in-one | 85182 |
| dna-proximal-policy-optimization-with-a-dual | 110962 |
| asynchronous-methods-for-deep-reinforcement | 28819.0 |
| a-distributional-perspective-on-reinforcement | 48192.0 |
| curl-contrastive-unsupervised-representations | 14280 |
| distributional-reinforcement-learning-with-1 | 76642 |
| online-and-offline-reinforcement-learning-by | 116726.96 |
| impala-scalable-distributed-deep-rl-with | 43375.50 |
| generalized-data-distribution-iteration | 1666665 |
| agent57-outperforming-the-atari-human | 206845.82 |
| implicit-quantile-networks-for-distributional | 73512 |
| self-imitation-learning | 34449.2 |
| mastering-atari-go-chess-and-shogi-by | 204824.00 |
| deep-reinforcement-learning-with-double-q | 37484.0 |
| dueling-network-architectures-for-deep | 34294.0 |
| recurrent-experience-replay-in-distributed | 233413.3 |
| distributed-prioritized-experience-replay | 97829.5 |
| human-level-control-through-deep | 23270.0 |
| 모델 43 | 29151.0 |