Atari Games On Atari 2600 Tennis
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 |
|---|---|
| 模型 1 | 0.0 |
| dueling-network-architectures-for-deep | 5.1 |
| train-a-real-world-local-path-planner-in-one | 22.3 |
| recurrent-rational-networks | 20.6 |
| policy-optimization-with-penalized-point | -8.32 |
| recurrent-experience-replay-in-distributed | -0.1 |
| recurrent-rational-networks | 20.5 |
| gdi-rethinking-what-makes-reinforcement | 24 |
| human-level-control-through-deep | -2.5 |
| agent57-outperforming-the-atari-human | 23.84 |
| deep-reinforcement-learning-with-double-q | 12.2 |
| implicit-quantile-networks-for-distributional | 23.6 |
| the-arcade-learning-environment-an-evaluation | 2.8 |
| massively-parallel-methods-for-deep | -0.7 |
| asynchronous-methods-for-deep-reinforcement | -6.4 |
| prioritized-experience-replay | -5.3 |
| mastering-atari-go-chess-and-shogi-by | 0.00 |
| evolution-strategies-as-a-scalable | -4.5 |
| distributional-reinforcement-learning-with-1 | 23.6 |
| deep-reinforcement-learning-with-double-q | 11.1 |
| deep-exploration-via-bootstrapped-dqn | 0 |
| learning-values-across-many-orders-of | 12.1 |
| a-distributional-perspective-on-reinforcement | 23.1 |
| asynchronous-methods-for-deep-reinforcement | -6.3 |
| dueling-network-architectures-for-deep | -22.8 |
| deep-reinforcement-learning-with-double-q | -13.2 |
| prioritized-experience-replay | 0.0 |
| generalized-data-distribution-iteration | 24 |
| dna-proximal-policy-optimization-with-a-dual | -10.9 |
| the-arcade-learning-environment-an-evaluation | -0.1 |
| mastering-atari-with-discrete-world-models-1 | 14 |
| generalized-data-distribution-iteration | 24 |
| impala-scalable-distributed-deep-rl-with | 0.55 |
| self-imitation-learning | -17.3 |
| online-and-offline-reinforcement-learning-by | 0 |
| deep-reinforcement-learning-with-double-q | -7.8 |
| asynchronous-methods-for-deep-reinforcement | -10.2 |
| distributed-prioritized-experience-replay | 23.9 |
| dueling-network-architectures-for-deep | 4.4 |
| noisy-networks-for-exploration | 0 |
| increasing-the-action-gap-new-operators-for | 0 |
| evolving-simple-programs-for-playing-atari | 0 |
| dueling-network-architectures-for-deep | 0.0 |