Atari Games On Atari 2600 Wizard Of Wor
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 |
|---|---|
| prioritized-experience-replay | 4802.0 |
| self-imitation-learning | 7088.3 |
| prioritized-experience-replay | 5727.0 |
| recurrent-experience-replay-in-distributed | 144362.7 |
| online-and-offline-reinforcement-learning-by | 100096.6 |
| mastering-atari-with-discrete-world-models-1 | 12851 |
| evolution-strategies-as-a-scalable | 3480.0 |
| the-arcade-learning-environment-an-evaluation | 1981.3 |
| learning-values-across-many-orders-of | 483.0 |
| generalized-data-distribution-iteration | 63735 |
| massively-parallel-methods-for-deep | 10431.0 |
| deep-reinforcement-learning-with-double-q | 2704.0 |
| distributed-prioritized-experience-replay | 46204 |
| generalized-data-distribution-iteration | 64239 |
| agent57-outperforming-the-atari-human | 157306.41 |
| dueling-network-architectures-for-deep | 12352.0 |
| the-arcade-learning-environment-an-evaluation | 105500 |
| noisy-networks-for-exploration | 9149 |
| human-level-control-through-deep | 3393.0 |
| deep-reinforcement-learning-with-double-q | 6201.0 |
| 模型 21 | 36.9 |
| mastering-atari-go-chess-and-shogi-by | 197126.00 |
| impala-scalable-distributed-deep-rl-with | 9157.50 |
| dna-proximal-policy-optimization-with-a-dual | 20851 |
| increasing-the-action-gap-new-operators-for | 9541.14 |
| distributional-reinforcement-learning-with-1 | 25061 |
| a-distributional-perspective-on-reinforcement | 9300.0 |
| dueling-network-architectures-for-deep | 7492.0 |
| deep-reinforcement-learning-with-double-q | 1609.0 |
| implicit-quantile-networks-for-distributional | 31190 |
| asynchronous-methods-for-deep-reinforcement | 5278.0 |
| evolving-simple-programs-for-playing-atari | 3820 |
| asynchronous-methods-for-deep-reinforcement | 18082.0 |
| dueling-network-architectures-for-deep | 7054.0 |
| dueling-network-architectures-for-deep | 7855.0 |
| fully-parameterized-quantile-function-for | 44782.6 |
| policy-optimization-with-penalized-point | 4704 |
| train-a-real-world-local-path-planner-in-one | 21049 |
| deep-reinforcement-learning-with-double-q | 10471.0 |
| deep-exploration-via-bootstrapped-dqn | 6804.7 |
| asynchronous-methods-for-deep-reinforcement | 17244.0 |