Continuous Control On Lunar Lander Openai Gym
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 |
|---|---|
| mean-actor-critic | 163.5 |
| addressing-function-approximation-error-in | 277.26±4.17 |
| continuous-control-with-deep-reinforcement | 256.98±14.38 |
| proximal-policy-optimization-algorithms | 175.14±44.94 |
| soft-actor-critic-off-policy-maximum-entropy | 284.59±0.97 |