Atari Games On Atari 2600 Alien
평가 지표
Score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Score |
|---|---|
| dna-proximal-policy-optimization-with-a-dual | 5021 |
| increasing-the-action-gap-new-operators-for | 5699.81 |
| dueling-network-architectures-for-deep | 3941.0 |
| self-imitation-learning | 2242.2 |
| asynchronous-methods-for-deep-reinforcement | 945.3 |
| generalized-data-distribution-iteration | 48735 |
| evolving-simple-programs-for-playing-atari | 1978 |
| the-arcade-learning-environment-an-evaluation | 939.2 |
| mastering-atari-go-chess-and-shogi-by | 741812.63 |
| recurrent-experience-replay-in-distributed | 229496.9 |
| massively-parallel-methods-for-deep | 813.5 |
| deep-reinforcement-learning-with-double-q | 1033.4 |
| asynchronous-methods-for-deep-reinforcement | 518.4 |
| prioritized-experience-replay | 4203.8 |
| soft-actor-critic-for-discrete-action | 216.9 |
| dueling-network-architectures-for-deep | 4461.4 |
| dueling-network-architectures-for-deep | 3747.7 |
| the-reactor-a-fast-and-sample-efficient-actor | 12689.1 |
| gdi-rethinking-what-makes-reinforcement-1 | 279700 |
| deep-exploration-via-bootstrapped-dqn | 2436.6 |
| learning-values-across-many-orders-of | 3213.5 |
| train-a-real-world-local-path-planner-in-one | 6955.2 |
| deep-reinforcement-learning-with-double-q | 634.0 |
| deep-reinforcement-learning-with-double-q | 823.7 |
| distributional-reinforcement-learning-with-1 | 4871 |
| dueling-network-architectures-for-deep | 823.7 |
| value-prediction-network | 1429 |
| asynchronous-methods-for-deep-reinforcement | 182.1 |
| 모델 29 | 103.2 |
| policy-optimization-with-penalized-point | 1510.8 |
| dueling-network-architectures-for-deep | 1486.5 |
| mastering-atari-with-discrete-world-models-1 | 3967 |
| impala-scalable-distributed-deep-rl-with | 15962.10 |
| generalized-data-distribution-iteration | 43384 |
| the-arcade-learning-environment-an-evaluation | 7785 |
| deep-reinforcement-learning-with-double-q | 1620.0 |
| implicit-quantile-networks-for-distributional | 7022 |
| increasing-the-action-gap-new-operators-for | 4990.91 |
| noisy-networks-for-exploration | 5778 |
| curl-contrastive-unsupervised-representations | 1148.2 |
| fully-parameterized-quantile-function-for | 16754.6 |
| prioritized-experience-replay | 1334.7 |
| online-and-offline-reinforcement-learning-by | 70192.35 |
| agent57-outperforming-the-atari-human | 297638.17 |
| a-distributional-perspective-on-reinforcement | 3166.0 |
| evolution-strategies-as-a-scalable | 994.0 |
| improving-computational-efficiency-in-visual | 1172.6 |
| human-level-control-through-deep | 3069.0 |
| distributed-prioritized-experience-replay | 40804.9 |