Atari Games On Atari 2600 Video Pinball
评估指标
Score
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Score |
|---|---|
| recurrent-rational-networks | 149712 |
| deep-reinforcement-learning-with-double-q | 154414.1 |
| deep-reinforcement-learning-with-double-q | 447408.6 |
| policy-optimization-with-penalized-point | 37780.7 |
| deep-reinforcement-learning-with-double-q | 367823.7 |
| a-distributional-perspective-on-reinforcement | 949604.0 |
| impala-scalable-distributed-deep-rl-with | 572898.27 |
| dueling-network-architectures-for-deep | 98209.5 |
| prioritized-experience-replay | 295972.8 |
| train-a-real-world-local-path-planner-in-one | 626794 |
| online-and-offline-reinforcement-learning-by | 865543.44 |
| distributed-prioritized-experience-replay | 565163.2 |
| learning-values-across-many-orders-of | 56287.0 |
| deep-reinforcement-learning-with-double-q | 196760.4 |
| asynchronous-methods-for-deep-reinforcement | 185852.6 |
| massively-parallel-methods-for-deep | 112093.4 |
| dueling-network-architectures-for-deep | 309941.9 |
| evolution-strategies-as-a-scalable | 22834.8 |
| recurrent-experience-replay-in-distributed | 999383.2 |
| dueling-network-architectures-for-deep | 479197.0 |
| implicit-quantile-networks-for-distributional | 698045 |
| the-arcade-learning-environment-an-evaluation | 254748 |
| agent57-outperforming-the-atari-human | 992340.74 |
| noisy-networks-for-exploration | 870954 |
| human-level-control-through-deep | 42684.0 |
| distributional-reinforcement-learning-with-1 | 705662 |
| increasing-the-action-gap-new-operators-for | 543504 |
| 模型 28 | 19761.0 |
| the-arcade-learning-environment-an-evaluation | 16871.3 |
| mastering-atari-with-discrete-world-models-1 | 41860 |
| self-imitation-learning | 461522.4 |
| prioritized-experience-replay | 282007.3 |
| recurrent-rational-networks | 86942 |
| deep-exploration-via-bootstrapped-dqn | 811610 |
| evolving-simple-programs-for-playing-atari | 33752.4 |
| asynchronous-methods-for-deep-reinforcement | 331628.1 |
| dna-proximal-policy-optimization-with-a-dual | 505392 |
| dueling-network-architectures-for-deep | 110976.2 |
| generalized-data-distribution-iteration | 925830 |
| asynchronous-methods-for-deep-reinforcement | 470310.5 |
| generalized-data-distribution-iteration | 978190 |
| mastering-atari-go-chess-and-shogi-by | 981791.88 |