Openai Gym On Walker2D V4
评估指标
Average Return
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 |
|---|---|
| soft-actor-critic-off-policy-maximum-entropy | 5745.27 |
| maximum-entropy-reinforcement-learning-via | 5526.66 |
| continuous-control-with-deep-reinforcement | 2994.54 |
| proximal-policy-optimization-algorithms | 2739.81 |
| addressing-function-approximation-error-in | 2612.74 |