Atari Games On Atari 2600 Road Runner
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 |
|---|---|
| curl-contrastive-unsupervised-representations | 6786.7 |
| mastering-atari-go-chess-and-shogi-by | 613411.80 |
| recurrent-experience-replay-in-distributed | 599246.7 |
| distributional-reinforcement-learning-with-1 | 64262 |
| a-distributional-perspective-on-reinforcement | 55839.0 |
| impala-scalable-distributed-deep-rl-with | 57121.00 |
| dueling-network-architectures-for-deep | 58549.0 |
| self-imitation-learning | 57071.7 |
| agent57-outperforming-the-atari-human | 243025.8 |
| implicit-quantile-networks-for-distributional | 57900 |
| deep-reinforcement-learning-with-double-q | 35215.0 |
| generalized-data-distribution-iteration | 999999 |
| the-arcade-learning-environment-an-evaluation | 67.7 |
| deep-reinforcement-learning-with-double-q | 54630.0 |
| deep-reinforcement-learning-with-double-q | 43156.0 |
| generalized-data-distribution-iteration | 878600 |
| dueling-network-architectures-for-deep | 69524.0 |
| dna-proximal-policy-optimization-with-a-dual | 61713 |
| soft-actor-critic-for-discrete-action | 305.3 |
| train-a-real-world-local-path-planner-in-one | 56520 |
| the-arcade-learning-environment-an-evaluation | 38725 |
| deep-reinforcement-learning-with-double-q | 39544.0 |
| mastering-atari-with-discrete-world-models-1 | 203576 |
| dueling-network-architectures-for-deep | 62151.0 |
| 模型 25 | 89.1 |
| increasing-the-action-gap-new-operators-for | 52351.23 |
| evolving-simple-programs-for-playing-atari | 8960 |
| prioritized-experience-replay | 52264.0 |
| learning-values-across-many-orders-of | 47770.0 |
| dueling-network-architectures-for-deep | 44127.0 |
| asynchronous-methods-for-deep-reinforcement | 73949.0 |
| distributed-prioritized-experience-replay | 222234.5 |
| evolution-strategies-as-a-scalable | 16590.0 |
| asynchronous-methods-for-deep-reinforcement | 34216.0 |
| deep-exploration-via-bootstrapped-dqn | 51500 |
| human-level-control-through-deep | 18257.0 |
| noisy-networks-for-exploration | 234352 |
| improving-computational-efficiency-in-visual | 11794 |
| asynchronous-methods-for-deep-reinforcement | 31769.0 |
| prioritized-experience-replay | 57608.0 |
| massively-parallel-methods-for-deep | 43079.8 |
| gdi-rethinking-what-makes-reinforcement | 878600 |
| online-and-offline-reinforcement-learning-by | 531097 |
| policy-optimization-with-penalized-point | 44679.67 |