Montezuma S Revenge On Atari 2600 Montezuma S
评估指标
Average Return (NoOp)
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 | Average Return (NoOp) |
|---|---|
| reinforcement-learning-with-latent-flow-1 | 900 |
| reinforcement-learning-with-latent-flow-1 | 1668 |
| rainbow-combining-improvements-in-deep | 384 |